{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/fairness/papers/14","list_of":"/task/fairness","task":"Fairness","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":14,"pages_in_order":57,"rows_per_page":100,"rows":[1301,1400],"of":5676,"counts":{"archive_papers_tagged":5676,"with_a_code_link":1714,"where_syntology_ran_a_sample":404,"not_listed_spam_title":0,"listed":5676,"listed_where_code_ran":404,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":329,"every_run_a_failure_of_syntologys_instrument":75,"listed_with_a_run_with_no_instrument_failure":329,"listed_every_run_a_failure_of_syntologys_instrument":75,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/fairness","prev":"/task/fairness/papers/13","next":"/task/fairness/papers/15","papers":[{"url":"/paper/on-causally-disentangled-representations","slug":"on-causally-disentangled-representations","title":"On Causally Disentangled Representations","date":"2021-12-10","arxiv_id":"2112.05746","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/on-causally-disentangled-representations#ran","syntology_url":"https://syntology.ai/paper/2112.05746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.05746"}},"official":{"repos":["causal-disentanglement/disentanglement_lib"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/counterfactual-fairness-in-mortgage-lending","slug":"counterfactual-fairness-in-mortgage-lending","title":"Counterfactual Fairness in Mortgage Lending via Matching and Randomization","date":"2021-12-03","arxiv_id":"2112.02170","repositories_listed":1,"syntology":null},{"url":"/paper/learning-optimal-predictive-checklists-1","slug":"learning-optimal-predictive-checklists-1","title":"Learning Optimal Predictive Checklists","date":"2021-12-02","arxiv_id":"2112.01020","repositories_listed":1,"syntology":null},{"url":"/paper/sampling-with-trusthworthy-constraints-a","slug":"sampling-with-trusthworthy-constraints-a","title":"Sampling with Trusthworthy Constraints: A Variational Gradient Framework","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/deformable-protopnet-an-interpretable-image","slug":"deformable-protopnet-an-interpretable-image","title":"Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes","date":"2021-11-29","arxiv_id":"2111.15000","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/deformable-protopnet-an-interpretable-image#ran","syntology_url":"https://syntology.ai/paper/2111.15000","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.15000"}},"official":{"repos":["jdonnelly36/Deformable-ProtoPNet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-fair-classifiers-with-partially","slug":"learning-fair-classifiers-with-partially","title":"Learning Fair Classifiers with Partially Annotated Group Labels","date":"2021-11-29","arxiv_id":"2111.14581","repositories_listed":1,"syntology":null},{"url":"/paper/the-impact-of-data-distribution-on-fairness","slug":"the-impact-of-data-distribution-on-fairness","title":"The Impact of Data Distribution on Fairness and Robustness in Federated Learning","date":"2021-11-29","arxiv_id":"2112.01274","repositories_listed":1,"syntology":null},{"url":"/paper/latent-space-smoothing-for-individually-fair-1","slug":"latent-space-smoothing-for-individually-fair-1","title":"Latent Space Smoothing for Individually Fair Representations","date":"2021-11-26","arxiv_id":"2111.13650","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/latent-space-smoothing-for-individually-fair-1#ran","syntology_url":"https://syntology.ai/paper/2111.13650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.13650"}},"official":{"repos":["eth-sri/lassi"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-debiased-models-with-dynamic","slug":"learning-debiased-models-with-dynamic","title":"Combating Unknown Bias with Effective Bias-Conflicting Scoring and Gradient Alignment","date":"2021-11-25","arxiv_id":"2111.13108","repositories_listed":1,"syntology":null},{"url":"/paper/towards-return-parity-in-markov-decision","slug":"towards-return-parity-in-markov-decision","title":"Towards Return Parity in Markov Decision Processes","date":"2021-11-19","arxiv_id":"2111.10476","repositories_listed":1,"syntology":null},{"url":"/paper/limecraft-handcrafted-superpixel-selection","slug":"limecraft-handcrafted-superpixel-selection","title":"LIMEcraft: Handcrafted superpixel selection and inspection for Visual eXplanations","date":"2021-11-15","arxiv_id":"2111.08094","repositories_listed":1,"syntology":null},{"url":"/paper/property-inference-attacks-against-gans","slug":"property-inference-attacks-against-gans","title":"Property Inference Attacks Against GANs","date":"2021-11-15","arxiv_id":"2111.07608","repositories_listed":1,"syntology":null},{"url":"/paper/can-information-flows-suggest-targets-for","slug":"can-information-flows-suggest-targets-for","title":"Can Information Flows Suggest Targets for Interventions in Neural Circuits?","date":"2021-11-09","arxiv_id":"2111.05299","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-information-flows-suggest-targets-for#ran","syntology_url":"https://syntology.ai/paper/2111.05299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.05299"}},"official":{"repos":["praveenv253/ann-info-flow"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/can-we-achieve-fairness-using-semi-supervised","slug":"can-we-achieve-fairness-using-semi-supervised","title":"Fair-SSL: Building fair ML Software with less data","date":"2021-11-03","arxiv_id":"2111.02038","repositories_listed":1,"syntology":null},{"url":"/paper/constructing-a-psychometric-testbed-for-fair","slug":"constructing-a-psychometric-testbed-for-fair","title":"Constructing a Psychometric Testbed for Fair Natural Language Processing","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/low-cost-algorithmic-recourse-for-users-with-1","slug":"low-cost-algorithmic-recourse-for-users-with-1","title":"Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions","date":"2021-11-01","arxiv_id":"2111.01235","repositories_listed":1,"syntology":null},{"url":"/paper/resource-efficient-federated-learning","slug":"resource-efficient-federated-learning","title":"Resource-Efficient Federated Learning","date":"2021-11-01","arxiv_id":"2111.01108","repositories_listed":1,"syntology":null},{"url":"/paper/fairer-entity-resolution-with-fairness","slug":"fairer-entity-resolution-with-fairness","title":"FairER: Entity Resolution with Fairness Constraints","date":"2021-10-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/selective-regression-under-fairness-criteria","slug":"selective-regression-under-fairness-criteria","title":"Selective Regression Under Fairness Criteria","date":"2021-10-28","arxiv_id":"2110.15403","repositories_listed":1,"syntology":null},{"url":"/paper/feature-and-label-embedding-spaces-matter-in","slug":"feature-and-label-embedding-spaces-matter-in","title":"Feature and Label Embedding Spaces Matter in Addressing Image Classifier Bias","date":"2021-10-27","arxiv_id":"2110.14336","repositories_listed":1,"syntology":null},{"url":"/paper/vaca-design-of-variational-graph-autoencoders","slug":"vaca-design-of-variational-graph-autoencoders","title":"VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries","date":"2021-10-27","arxiv_id":"2110.14690","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vaca-design-of-variational-graph-autoencoders#ran","syntology_url":"https://syntology.ai/paper/2110.14690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14690"}},"official":{"repos":["psanch21/VACA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/boosted-cvar-classification","slug":"boosted-cvar-classification","title":"Boosted CVaR Classification","date":"2021-10-26","arxiv_id":"2110.13948","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/boosted-cvar-classification#ran","syntology_url":"https://syntology.ai/paper/2110.13948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13948"}},"official":{"repos":["runtianz/boosted_cvar"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fair-sequential-selection-using-supervised","slug":"fair-sequential-selection-using-supervised","title":"Fair Sequential Selection Using Supervised Learning Models","date":"2021-10-26","arxiv_id":"2110.13986","repositories_listed":1,"syntology":null},{"url":"/paper/post-processing-for-individual-fairness","slug":"post-processing-for-individual-fairness","title":"Post-processing for Individual Fairness","date":"2021-10-26","arxiv_id":"2110.13796","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/post-processing-for-individual-fairness#ran","syntology_url":"https://syntology.ai/paper/2110.13796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13796"}},"official":{"repos":["felix-petersen/fairness-post-processing"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-data-debiasing-through-bounded","slug":"adaptive-data-debiasing-through-bounded","title":"Adaptive Data Debiasing through Bounded Exploration","date":"2021-10-25","arxiv_id":"2110.13054","repositories_listed":1,"syntology":null},{"url":"/paper/decaf-generating-fair-synthetic-data-using","slug":"decaf-generating-fair-synthetic-data-using","title":"DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks","date":"2021-10-25","arxiv_id":"2110.12884","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/decaf-generating-fair-synthetic-data-using#ran","syntology_url":"https://syntology.ai/paper/2110.12884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.12884"}},"official":{"repos":["vanderschaarlab/decaf"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fair-enough-searching-for-sufficient-measures","slug":"fair-enough-searching-for-sufficient-measures","title":"Fair Enough: Searching for Sufficient Measures of Fairness","date":"2021-10-25","arxiv_id":"2110.13029","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fair-enough-searching-for-sufficient-measures#ran","syntology_url":"https://syntology.ai/paper/2110.13029","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.13029"}},"official":{"repos":["repoanonymous/fairness_metrics"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fdgatii-fast-dynamic-graph-attention-with","slug":"fdgatii-fast-dynamic-graph-attention-with","title":"FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping","date":"2021-10-21","arxiv_id":"2110.11464","repositories_listed":1,"syntology":null},{"url":"/paper/aequevox-automated-fairness-testing-of-speech","slug":"aequevox-automated-fairness-testing-of-speech","title":"AequeVox: Automated Fairness Testing of Speech Recognition Systems","date":"2021-10-19","arxiv_id":"2110.09843","repositories_listed":1,"syntology":null},{"url":"/paper/fair-tree-learning","slug":"fair-tree-learning","title":"Fair Tree Classifier using Strong Demographic Parity","date":"2021-10-18","arxiv_id":"2110.09295","repositories_listed":1,"syntology":null},{"url":"/paper/developing-a-novel-fair-loan-predictor","slug":"developing-a-novel-fair-loan-predictor","title":"Developing a novel fair-loan-predictor through a multi-sensitive debiasing pipeline: DualFair","date":"2021-10-17","arxiv_id":"2110.08944","repositories_listed":1,"syntology":null},{"url":"/paper/magnet-uniform-sampling-from-deep-generative-1","slug":"magnet-uniform-sampling-from-deep-generative-1","title":"MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining","date":"2021-10-15","arxiv_id":"2110.08009","repositories_listed":1,"syntology":null},{"url":"/paper/user-experiences-oriented-sightseeing-spot","slug":"user-experiences-oriented-sightseeing-spot","title":"Recommending POIs for Tourists by User Behavior Modeling and Pseudo-Rating","date":"2021-10-13","arxiv_id":"2110.06523","repositories_listed":1,"syntology":null},{"url":"/paper/the-rich-get-richer-disparate-impact-of-semi-1","slug":"the-rich-get-richer-disparate-impact-of-semi-1","title":"The Rich Get Richer: Disparate Impact of Semi-Supervised Learning","date":"2021-10-12","arxiv_id":"2110.06282","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/the-rich-get-richer-disparate-impact-of-semi-1#ran","syntology_url":"https://syntology.ai/paper/2110.06282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.06282"}},"official":{"repos":["ucsc-real/disparate-ssl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/distinguishing-rule-and-exemplar-based-1","slug":"distinguishing-rule-and-exemplar-based-1","title":"Distinguishing rule- and exemplar-based generalization in learning systems","date":"2021-10-08","arxiv_id":"2110.04328","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/distinguishing-rule-and-exemplar-based-1#ran","syntology_url":"https://syntology.ai/paper/2110.04328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04328"}},"official":{"repos":["eringrant/icml-2022-rules-vs-exemplars"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/data-driven-methods-for-balancing-fairness","slug":"data-driven-methods-for-balancing-fairness","title":"Data-Driven Methods for Balancing Fairness and Efficiency in Ride-Pooling","date":"2021-10-07","arxiv_id":"2110.03524","repositories_listed":1,"syntology":null},{"url":"/paper/collective-explainable-ai-explaining","slug":"collective-explainable-ai-explaining","title":"Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning with Shapley Values","date":"2021-10-04","arxiv_id":"2110.01307","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-model-robustness-and-fairness-with","slug":"enhancing-model-robustness-and-fairness-with","title":"Enhancing Model Robustness and Fairness with Causality: A Regularization Approach","date":"2021-10-03","arxiv_id":"2110.00911","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-datasets-for-fairness-aware","slug":"a-survey-on-datasets-for-fairness-aware","title":"A survey on datasets for fairness-aware machine learning","date":"2021-10-01","arxiv_id":"2110.00530","repositories_listed":1,"syntology":null},{"url":"/paper/generalized-demographic-parity-for-group","slug":"generalized-demographic-parity-for-group","title":"Generalized Demographic Parity for Group Fairness","date":"2021-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-racial-biases-in-toxic-language","slug":"mitigating-racial-biases-in-toxic-language","title":"Mitigating Racial Biases in Toxic Language Detection with an Equity-Based Ensemble Framework","date":"2021-09-27","arxiv_id":"2109.13137","repositories_listed":1,"syntology":null},{"url":"/paper/equality-of-opportunity-in-travel-behavior","slug":"equality-of-opportunity-in-travel-behavior","title":"Equality of opportunity in travel behavior prediction with deep neural networks and discrete choice models","date":"2021-09-25","arxiv_id":"2109.12422","repositories_listed":1,"syntology":null},{"url":"/paper/sd-qa-spoken-dialectal-question-answering-for","slug":"sd-qa-spoken-dialectal-question-answering-for","title":"SD-QA: Spoken Dialectal Question Answering for the Real World","date":"2021-09-24","arxiv_id":"2109.12072","repositories_listed":1,"syntology":{"n":22,"n_ran":20,"n_constructed":0,"n_ran_checked":20,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":20,"n_pointer_only":0,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 0 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sd-qa-spoken-dialectal-question-answering-for#ran","syntology_url":"https://syntology.ai/paper/2109.12072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.12072"}},"official":{"repos":["ffaisal93/sd-qa"],"state":"official (archive's flag): 20 ran","n_ran":20,"n_constructed":0,"n_ran_no_instrument_failure":20,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ds-net-dynamic-weight-slicing-for-efficient","slug":"ds-net-dynamic-weight-slicing-for-efficient","title":"DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers","date":"2021-09-21","arxiv_id":"2109.10060","repositories_listed":1,"syntology":null},{"url":"/paper/algorithmic-fairness-verification-with","slug":"algorithmic-fairness-verification-with","title":"Algorithmic Fairness Verification with Graphical Models","date":"2021-09-20","arxiv_id":"2109.09447","repositories_listed":1,"syntology":null},{"url":"/paper/towards-automatic-bias-detection-in-knowledge","slug":"towards-automatic-bias-detection-in-knowledge","title":"Towards Automatic Bias Detection in Knowledge Graphs","date":"2021-09-19","arxiv_id":"2109.10697","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-be-fair-a-consequentialist","slug":"learning-to-be-fair-a-consequentialist","title":"Learning to be Fair: A Consequentialist Approach to Equitable Decision-Making","date":"2021-09-18","arxiv_id":"2109.08792","repositories_listed":1,"syntology":null},{"url":"/paper/achieving-model-fairness-in-vertical","slug":"achieving-model-fairness-in-vertical","title":"Achieving Model Fairness in Vertical Federated Learning","date":"2021-09-17","arxiv_id":"2109.08344","repositories_listed":1,"syntology":null},{"url":"/paper/measuring-fairness-under-unawareness-via","slug":"measuring-fairness-under-unawareness-via","title":"Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach","date":"2021-09-17","arxiv_id":"2109.08549","repositories_listed":1,"syntology":null},{"url":"/paper/on-tilted-losses-in-machine-learning-theory","slug":"on-tilted-losses-in-machine-learning-theory","title":"On Tilted Losses in Machine Learning: Theory and Applications","date":"2021-09-13","arxiv_id":"2109.06141","repositories_listed":1,"syntology":null},{"url":"/paper/fairness-without-the-sensitive-attribute-via","slug":"fairness-without-the-sensitive-attribute-via","title":"Fairness without the sensitive attribute via Causal Variational Autoencoder","date":"2021-09-10","arxiv_id":"2109.04999","repositories_listed":1,"syntology":null},{"url":"/paper/style-pooling-automatic-text-style","slug":"style-pooling-automatic-text-style","title":"Style Pooling: Automatic Text Style Obfuscation for Improved Classification Fairness","date":"2021-09-10","arxiv_id":"2109.04624","repositories_listed":1,"syntology":null},{"url":"/paper/gradual-in-compatibility-of-fairness-criteria","slug":"gradual-in-compatibility-of-fairness-criteria","title":"Gradual (In)Compatibility of Fairness Criteria","date":"2021-09-09","arxiv_id":"2109.04399","repositories_listed":1,"syntology":null},{"url":"/paper/attributing-fair-decisions-with-attention","slug":"attributing-fair-decisions-with-attention","title":"Attributing Fair Decisions with Attention Interventions","date":"2021-09-08","arxiv_id":"2109.03952","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-fundamental-trade-offs-in-learning","slug":"on-the-fundamental-trade-offs-in-learning","title":"On Characterizing the Trade-off in Invariant Representation Learning","date":"2021-09-08","arxiv_id":"2109.03386","repositories_listed":1,"syntology":null},{"url":"/paper/amazon-sagemaker-clarify-machine-learning","slug":"amazon-sagemaker-clarify-machine-learning","title":"Amazon SageMaker Clarify: Machine Learning Bias Detection and Explainability in the Cloud","date":"2021-09-07","arxiv_id":"2109.03285","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/amazon-sagemaker-clarify-machine-learning#ran","syntology_url":"https://syntology.ai/paper/2109.03285","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.03285"}},"official":{"repos":["aws/amazon-sagemaker-clarify"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-based-downlink-power-allocation-in","slug":"learning-based-downlink-power-allocation-in","title":"Learning-Based Downlink Power Allocation in Cell-Free Massive MIMO Systems","date":"2021-09-07","arxiv_id":"2109.03128","repositories_listed":1,"syntology":null},{"url":"/paper/fair-federated-learning-for-heterogeneous","slug":"fair-federated-learning-for-heterogeneous","title":"F3: Fair and Federated Face Attribute Classification with Heterogeneous Data","date":"2021-09-06","arxiv_id":"2109.02351","repositories_listed":1,"syntology":null},{"url":"/paper/causal-inference-in-natural-language","slug":"causal-inference-in-natural-language","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","date":"2021-09-02","arxiv_id":"2109.00725","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-algorithms-for-fair-clustering-with","slug":"efficient-algorithms-for-fair-clustering-with","title":"Efficient Algorithms For Fair Clustering with a New Fairness Notion","date":"2021-09-02","arxiv_id":"2109.00708","repositories_listed":1,"syntology":null},{"url":"/paper/tabfairgan-fair-tabular-data-generation-with","slug":"tabfairgan-fair-tabular-data-generation-with","title":"TabFairGAN: Fair Tabular Data Generation with Generative Adversarial Networks","date":"2021-09-02","arxiv_id":"2109.00666","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tabfairgan-fair-tabular-data-generation-with#ran","syntology_url":"https://syntology.ai/paper/2109.00666","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.00666"}},"official":{"repos":["amirarsalan90/TabFairGAN"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fade-fair-double-ensemble-learning-for","slug":"fade-fair-double-ensemble-learning-for","title":"FADE: FAir Double Ensemble Learning for Observable and Counterfactual Outcomes","date":"2021-09-01","arxiv_id":"2109.00173","repositories_listed":1,"syntology":null},{"url":"/paper/fair-representation-guaranteeing-approximate","slug":"fair-representation-guaranteeing-approximate","title":"Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks","date":"2021-09-01","arxiv_id":"2109.00545","repositories_listed":1,"syntology":null},{"url":"/paper/learning-optimal-prescriptive-trees-from","slug":"learning-optimal-prescriptive-trees-from","title":"Learning Optimal Prescriptive Trees from Observational Data","date":"2021-08-31","arxiv_id":"2108.13628","repositories_listed":1,"syntology":null},{"url":"/paper/transport-based-counterfactual-models","slug":"transport-based-counterfactual-models","title":"Transport-based Counterfactual Models","date":"2021-08-30","arxiv_id":"2108.13025","repositories_listed":1,"syntology":null},{"url":"/paper/federated-learning-meets-fairness-and","slug":"federated-learning-meets-fairness-and","title":"Federated Learning Meets Fairness and Differential Privacy","date":"2021-08-23","arxiv_id":"2108.09932","repositories_listed":1,"syntology":null},{"url":"/paper/eqgnn-equalized-node-opportunity-in-graphs","slug":"eqgnn-equalized-node-opportunity-in-graphs","title":"EqGNN: Equalized Node Opportunity in Graphs","date":"2021-08-19","arxiv_id":"2108.08800","repositories_listed":1,"syntology":null},{"url":"/paper/fair-and-consistent-federated-learning","slug":"fair-and-consistent-federated-learning","title":"Addressing Algorithmic Disparity and Performance Inconsistency in Federated Learning","date":"2021-08-19","arxiv_id":"2108.08435","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fair-and-consistent-federated-learning#ran","syntology_url":"https://syntology.ai/paper/2108.08435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.08435"}},"official":{"repos":["cuis15/FCFL"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fairness-through-counterfactual-utilities","slug":"fairness-through-counterfactual-utilities","title":"Fairness Through Counterfactual Utilities","date":"2021-08-11","arxiv_id":"2108.05315","repositories_listed":1,"syntology":null},{"url":"/paper/zpy-open-source-synthetic-data-for-computer","slug":"zpy-open-source-synthetic-data-for-computer","title":"ZPY: Open Source Synthetic Data for Computer Vision","date":"2021-08-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fairness-properties-of-face-recognition-and","slug":"fairness-properties-of-face-recognition-and","title":"Fairness Properties of Face Recognition and Obfuscation Systems","date":"2021-08-05","arxiv_id":"2108.02707","repositories_listed":1,"syntology":null},{"url":"/paper/the-devil-is-in-the-gan-defending-deep","slug":"the-devil-is-in-the-gan-defending-deep","title":"The Devil is in the GAN: Backdoor Attacks and Defenses in Deep Generative Models","date":"2021-08-03","arxiv_id":"2108.01644","repositories_listed":1,"syntology":null},{"url":"/paper/counterfactual-inference-for-text","slug":"counterfactual-inference-for-text","title":"Counterfactual Inference for Text Classification Debiasing","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-fairness-analysis-of-abusive","slug":"fine-grained-fairness-analysis-of-abusive","title":"Fine-Grained Fairness Analysis of Abusive Language Detection Systems with CheckList","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/debiased-explainable-pairwise-ranking-from","slug":"debiased-explainable-pairwise-ranking-from","title":"Debiased Explainable Pairwise Ranking from Implicit Feedback","date":"2021-07-30","arxiv_id":"2107.14768","repositories_listed":1,"syntology":null},{"url":"/paper/fair-balance-mitigating-machine-learning-bias","slug":"fair-balance-mitigating-machine-learning-bias","title":"FairBalance: How to Achieve Equalized Odds With Data Pre-processing","date":"2021-07-17","arxiv_id":"2107.08310","repositories_listed":1,"syntology":null},{"url":"/paper/measuring-fairness-in-generative-models","slug":"measuring-fairness-in-generative-models","title":"Measuring Fairness in Generative Models","date":"2021-07-16","arxiv_id":"2107.07754","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/measuring-fairness-in-generative-models#ran","syntology_url":"https://syntology.ai/paper/2107.07754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07754"}},"official":{"repos":["Bearwithchris/Fairness_Metric"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fairness-in-ranking-under-uncertainty","slug":"fairness-in-ranking-under-uncertainty","title":"Fairness in Ranking under Uncertainty","date":"2021-07-14","arxiv_id":"2107.06720","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/fairness-in-ranking-under-uncertainty#ran","syntology_url":"https://syntology.ai/paper/2107.06720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.06720"}},"official":{"repos":["ashudeep/ranking-fairness-uncertainty"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/can-less-be-more-when-increasing-to-balancing","slug":"can-less-be-more-when-increasing-to-balancing","title":"Can Less be More? When Increasing-to-Balancing Label Noise Rates Considered Beneficial","date":"2021-07-13","arxiv_id":"2107.05913","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/can-less-be-more-when-increasing-to-balancing#ran","syntology_url":"https://syntology.ai/paper/2107.05913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.05913"}},"official":{"repos":["ucsc-real/canlessbemore"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/divine-diverse-influential-training-points","slug":"divine-diverse-influential-training-points","title":"DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement","date":"2021-07-13","arxiv_id":"2107.05978","repositories_listed":1,"syntology":null},{"url":"/paper/strategic-instrumental-variable-regression","slug":"strategic-instrumental-variable-regression","title":"Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses","date":"2021-07-12","arxiv_id":"2107.05762","repositories_listed":1,"syntology":null},{"url":"/paper/subgroup-generalization-and-fairness-of-graph","slug":"subgroup-generalization-and-fairness-of-graph","title":"Subgroup Generalization and Fairness of Graph Neural Networks","date":"2021-06-29","arxiv_id":"2106.15535","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/subgroup-generalization-and-fairness-of-graph#ran","syntology_url":"https://syntology.ai/paper/2106.15535","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.15535"}},"official":{"repos":["theaperdeng/gnn-generalization-fairness"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/quantifying-social-biases-in-nlp-a","slug":"quantifying-social-biases-in-nlp-a","title":"Quantifying Social Biases in NLP: A Generalization and Empirical Comparison of Extrinsic Fairness Metrics","date":"2021-06-28","arxiv_id":"2106.14574","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/quantifying-social-biases-in-nlp-a#ran","syntology_url":"https://syntology.ai/paper/2106.14574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.14574"}},"official":null}},{"url":"/paper/towards-understanding-and-mitigating-social","slug":"towards-understanding-and-mitigating-social","title":"Towards Understanding and Mitigating Social Biases in Language Models","date":"2021-06-24","arxiv_id":"2106.13219","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/towards-understanding-and-mitigating-social#ran","syntology_url":"https://syntology.ai/paper/2106.13219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13219"}},"official":{"repos":["pliang279/LM_bias"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/better-algorithms-for-individually-fair-k","slug":"better-algorithms-for-individually-fair-k","title":"Better Algorithms for Individually Fair $k$-Clustering","date":"2021-06-23","arxiv_id":"2106.12150","repositories_listed":1,"syntology":null},{"url":"/paper/fairness-for-image-generation-with-uncertain","slug":"fairness-for-image-generation-with-uncertain","title":"Fairness for Image Generation with Uncertain Sensitive Attributes","date":"2021-06-23","arxiv_id":"2106.12182","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/fairness-for-image-generation-with-uncertain#ran","syntology_url":"https://syntology.ai/paper/2106.12182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12182"}},"official":{"repos":["ajiljalal/code-cs-fairness"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/dp-sgd-vs-pate-which-has-less-disparate","slug":"dp-sgd-vs-pate-which-has-less-disparate","title":"DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?","date":"2021-06-22","arxiv_id":"2106.12576","repositories_listed":1,"syntology":null},{"url":"/paper/flea-provably-fair-multisource-learning-from","slug":"flea-provably-fair-multisource-learning-from","title":"FLEA: Provably Robust Fair Multisource Learning from Unreliable Training Data","date":"2021-06-22","arxiv_id":"2106.11732","repositories_listed":1,"syntology":null},{"url":"/paper/pysentimiento-a-python-toolkit-for-sentiment","slug":"pysentimiento-a-python-toolkit-for-sentiment","title":"pysentimiento: A Python Toolkit for Opinion Mining and Social NLP tasks","date":"2021-06-17","arxiv_id":"2106.09462","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-mixture-of-posteriors-for","slug":"contrastive-mixture-of-posteriors-for","title":"Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness","date":"2021-06-15","arxiv_id":"2106.08161","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":1,"n_ran_checked":6,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/contrastive-mixture-of-posteriors-for#ran","syntology_url":"https://syntology.ai/paper/2106.08161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.08161"}},"official":{"repos":["benevolentai/comp"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":1,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/simon-says-evaluating-and-mitigating-bias-in","slug":"simon-says-evaluating-and-mitigating-bias-in","title":"Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation","date":"2021-06-15","arxiv_id":"2106.07849","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/simon-says-evaluating-and-mitigating-bias-in#ran","syntology_url":"https://syntology.ai/paper/2106.07849","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07849"}},"official":{"repos":["codestar12/pruning-distilation-bias"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/characterizing-the-risk-of-fairwashing","slug":"characterizing-the-risk-of-fairwashing","title":"Characterizing the risk of fairwashing","date":"2021-06-14","arxiv_id":"2106.07504","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/characterizing-the-risk-of-fairwashing#ran","syntology_url":"https://syntology.ai/paper/2106.07504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07504"}},"official":{"repos":["aivodji/characterizing_fairwashing"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/planning-to-fairly-allocate-probabilistic","slug":"planning-to-fairly-allocate-probabilistic","title":"Planning to Fairly Allocate: Probabilistic Fairness in the Restless Bandit Setting","date":"2021-06-14","arxiv_id":"2106.07677","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/planning-to-fairly-allocate-probabilistic#ran","syntology_url":"https://syntology.ai/paper/2106.07677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07677"}},"official":{"repos":["crherlihy/prob_fair_rmab"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/achieving-diverse-objectives-with-ai-driven","slug":"achieving-diverse-objectives-with-ai-driven","title":"AI-driven Prices for Externalities and Sustainability in Production Markets","date":"2021-06-10","arxiv_id":"2106.06060","repositories_listed":1,"syntology":null},{"url":"/paper/consistent-instance-false-positive-improves","slug":"consistent-instance-false-positive-improves","title":"Consistent Instance False Positive Improves Fairness in Face Recognition","date":"2021-06-10","arxiv_id":"2106.05519","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/consistent-instance-false-positive-improves#ran","syntology_url":"https://syntology.ai/paper/2106.05519","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05519"}},"official":{"repos":["Tencent/TFace"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/fair-classification-with-adversarial","slug":"fair-classification-with-adversarial","title":"Fair Classification with Adversarial Perturbations","date":"2021-06-10","arxiv_id":"2106.05964","repositories_listed":1,"syntology":null},{"url":"/paper/fair-normalizing-flows","slug":"fair-normalizing-flows","title":"Fair Normalizing Flows","date":"2021-06-10","arxiv_id":"2106.05937","repositories_listed":1,"syntology":null},{"url":"/paper/a-new-notion-of-individually-fair-clustering","slug":"a-new-notion-of-individually-fair-clustering","title":"A New Notion of Individually Fair Clustering: $α$-Equitable $k$-Center","date":"2021-06-09","arxiv_id":"2106.05423","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-new-notion-of-individually-fair-clustering#ran","syntology_url":"https://syntology.ai/paper/2106.05423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05423"}},"official":{"repos":["chakrabarti/equitable_clustering"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-clustering-based-fair-outlier-detection","slug":"deep-clustering-based-fair-outlier-detection","title":"Deep Clustering based Fair Outlier Detection","date":"2021-06-09","arxiv_id":"2106.05127","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-clustering-based-fair-outlier-detection#ran","syntology_url":"https://syntology.ai/paper/2106.05127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05127"}},"official":{"repos":["brandeis-machine-learning/FairOutlierDetection"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-bias-mitigation-algorithms-in","slug":"benchmarking-bias-mitigation-algorithms-in","title":"Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness Metrics","date":"2021-06-08","arxiv_id":null,"repositories_listed":1,"syntology":null}],"record_sha256":"88f65d7167e4cd036383b4c60c121cbcdfd556b818c99d75195851e29ae6c097","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}