{"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/network-pruning/papers/2","list_of":"/task/network-pruning","task":"Network Pruning","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":2,"pages_in_order":6,"rows_per_page":100,"rows":[101,200],"of":534,"counts":{"archive_papers_tagged":534,"with_a_code_link":239,"where_syntology_ran_a_sample":83,"not_listed_spam_title":0,"listed":534,"listed_where_code_ran":83,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":65,"every_run_a_failure_of_syntologys_instrument":18,"listed_with_a_run_with_no_instrument_failure":65,"listed_every_run_a_failure_of_syntologys_instrument":18,"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/network-pruning","prev":"/task/network-pruning","next":"/task/network-pruning/papers/3","papers":[{"url":"/paper/pruning-deep-neural-networks-from-a-sparsity-1","slug":"pruning-deep-neural-networks-from-a-sparsity-1","title":"Pruning Deep Neural Networks from a Sparsity Perspective","date":"2023-02-11","arxiv_id":"2302.05601","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/pruning-deep-neural-networks-from-a-sparsity-1#ran","syntology_url":"https://syntology.ai/paper/2302.05601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.05601"}},"official":{"repos":["diaoenmao/pruning-deep-neural-networks-from-a-sparsity-perspective"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-search-and-training-for-robust-and","slug":"adaptive-search-and-training-for-robust-and","title":"Adaptive Search-and-Training for Robust and Efficient Network Pruning","date":"2023-02-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/depgraph-towards-any-structural-pruning","slug":"depgraph-towards-any-structural-pruning","title":"DepGraph: Towards Any Structural Pruning","date":"2023-01-30","arxiv_id":"2301.12900","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/depgraph-towards-any-structural-pruning#ran","syntology_url":"https://syntology.ai/paper/2301.12900","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12900"}},"official":{"repos":["VainF/Torch-Pruning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-latency-aware-cnn-depth-compression","slug":"efficient-latency-aware-cnn-depth-compression","title":"Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming","date":"2023-01-28","arxiv_id":"2301.12187","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/efficient-latency-aware-cnn-depth-compression#ran","syntology_url":"https://syntology.ai/paper/2301.12187","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12187"}},"official":{"repos":["snu-mllab/efficient-cnn-depth-compression"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/accelerating-and-compressing-deep-neural","slug":"accelerating-and-compressing-deep-neural","title":"Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI Feedback","date":"2023-01-20","arxiv_id":"2304.01914","repositories_listed":1,"syntology":null},{"url":"/paper/cross-model-comparative-loss-for-enhancing","slug":"cross-model-comparative-loss-for-enhancing","title":"Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language Understanding","date":"2023-01-10","arxiv_id":"2301.03765","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-network-pruning-via-hilbert-schmidt","slug":"automatic-network-pruning-via-hilbert-schmidt","title":"Automatic Network Pruning via Hilbert-Schmidt Independence Criterion Lasso under Information Bottleneck Principle","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/magnitude-and-similarity-based-variable-rate","slug":"magnitude-and-similarity-based-variable-rate","title":"Magnitude and Similarity based Variable Rate Filter Pruning for Efficient Convolution Neural Networks","date":"2022-12-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/are-straight-through-gradients-and-soft","slug":"are-straight-through-gradients-and-soft","title":"Are Straight-Through gradients and Soft-Thresholding all you need for Sparse Training?","date":"2022-12-02","arxiv_id":"2212.01076","repositories_listed":1,"syntology":null},{"url":"/paper/on-designing-light-weight-object-trackers","slug":"on-designing-light-weight-object-trackers","title":"On Designing Light-Weight Object Trackers through Network Pruning: Use CNNs or Transformers?","date":"2022-11-24","arxiv_id":"2211.13769","repositories_listed":1,"syntology":null},{"url":"/paper/a-fair-loss-function-for-network-pruning","slug":"a-fair-loss-function-for-network-pruning","title":"A Fair Loss Function for Network Pruning","date":"2022-11-18","arxiv_id":"2211.10285","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":5,"n_ran_checked":6,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":12,"phrase":"8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/a-fair-loss-function-for-network-pruning#ran","syntology_url":"https://syntology.ai/paper/2211.10285","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10285"}},"official":{"repos":["robbiemeyer/pw_loss_pruning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/finding-skill-neurons-in-pre-trained","slug":"finding-skill-neurons-in-pre-trained","title":"Finding Skill Neurons in Pre-trained Transformer-based Language Models","date":"2022-11-14","arxiv_id":"2211.07349","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/finding-skill-neurons-in-pre-trained#ran","syntology_url":"https://syntology.ai/paper/2211.07349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.07349"}},"official":{"repos":["thu-keg/skill-neuron"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-pruning-method-based-on-the-dissimilarity","slug":"a-pruning-method-based-on-the-dissimilarity","title":"A pruning method based on the dissimilarity of angle among channels and filters","date":"2022-10-29","arxiv_id":"2210.16504","repositories_listed":1,"syntology":null},{"url":"/paper/pp-structurev2-a-stronger-document-analysis","slug":"pp-structurev2-a-stronger-document-analysis","title":"PP-StructureV2: A Stronger Document Analysis System","date":"2022-10-11","arxiv_id":"2210.05391","repositories_listed":1,"syntology":null},{"url":"/paper/sparseadapter-an-easy-approach-for-improving","slug":"sparseadapter-an-easy-approach-for-improving","title":"SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters","date":"2022-10-09","arxiv_id":"2210.04284","repositories_listed":1,"syntology":null},{"url":"/paper/is-complexity-required-for-neural-network","slug":"is-complexity-required-for-neural-network","title":"Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude Pruning","date":"2022-09-29","arxiv_id":"2209.14624","repositories_listed":1,"syntology":null},{"url":"/paper/neural-network-panning-screening-the-optimal","slug":"neural-network-panning-screening-the-optimal","title":"Neural Network Panning: Screening the Optimal Sparse Network Before Training","date":"2022-09-27","arxiv_id":"2209.13378","repositories_listed":1,"syntology":null},{"url":"/paper/interpretations-steered-network-pruning-via","slug":"interpretations-steered-network-pruning-via","title":"Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps","date":"2022-09-07","arxiv_id":"2209.02869","repositories_listed":1,"syntology":null},{"url":"/paper/trainability-preserving-neural-structured","slug":"trainability-preserving-neural-structured","title":"Trainability Preserving Neural Pruning","date":"2022-07-25","arxiv_id":"2207.12534","repositories_listed":1,"syntology":null},{"url":"/paper/pr-darts-pruning-based-differentiable","slug":"pr-darts-pruning-based-differentiable","title":"DASS: Differentiable Architecture Search for Sparse neural networks","date":"2022-07-14","arxiv_id":"2207.06968","repositories_listed":1,"syntology":null},{"url":"/paper/network-pruning-via-feature-shift","slug":"network-pruning-via-feature-shift","title":"Network Pruning via Feature Shift Minimization","date":"2022-07-06","arxiv_id":"2207.02632","repositories_listed":1,"syntology":null},{"url":"/paper/specializing-pre-trained-language-models-for","slug":"specializing-pre-trained-language-models-for","title":"Specializing Pre-trained Language Models for Better Relational Reasoning via Network Pruning","date":"2022-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/studying-the-impact-of-magnitude-pruning-on","slug":"studying-the-impact-of-magnitude-pruning-on","title":"Studying the impact of magnitude pruning on contrastive learning methods","date":"2022-07-01","arxiv_id":"2207.00200","repositories_listed":1,"syntology":null},{"url":"/paper/winning-the-lottery-ahead-of-time-efficient","slug":"winning-the-lottery-ahead-of-time-efficient","title":"Winning the Lottery Ahead of Time: Efficient Early Network Pruning","date":"2022-06-21","arxiv_id":"2206.10451","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/winning-the-lottery-ahead-of-time-efficient#ran","syntology_url":"https://syntology.ai/paper/2206.10451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.10451"}},"official":{"repos":["johnrachwan123/Early-Cropression-via-Gradient-Flow-Preservation"],"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/sparse-double-descent-where-network-pruning","slug":"sparse-double-descent-where-network-pruning","title":"Sparse Double Descent: Where Network Pruning Aggravates Overfitting","date":"2022-06-17","arxiv_id":"2206.08684","repositories_listed":1,"syntology":null},{"url":"/paper/can-pruning-improve-certified-robustness-of","slug":"can-pruning-improve-certified-robustness-of","title":"Can pruning improve certified robustness of neural networks?","date":"2022-06-15","arxiv_id":"2206.07311","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-for-interpretable-feature-preserving","slug":"pruning-for-interpretable-feature-preserving","title":"Pruning for Feature-Preserving Circuits in CNNs","date":"2022-06-03","arxiv_id":"2206.01627","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-as-search-efficient-neural","slug":"pruning-as-search-efficient-neural","title":"Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization","date":"2022-06-02","arxiv_id":"2206.01198","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/pruning-as-search-efficient-neural#ran","syntology_url":"https://syntology.ai/paper/2206.01198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01198"}},"official":null}},{"url":"/paper/spartan-differentiable-sparsity-via","slug":"spartan-differentiable-sparsity-via","title":"Spartan: Differentiable Sparsity via Regularized Transportation","date":"2022-05-27","arxiv_id":"2205.14107","repositories_listed":1,"syntology":null},{"url":"/paper/compression-aware-training-of-neural-networks","slug":"compression-aware-training-of-neural-networks","title":"Compression-aware Training of Neural Networks using Frank-Wolfe","date":"2022-05-24","arxiv_id":"2205.11921","repositories_listed":1,"syntology":null},{"url":"/paper/quarantine-sparsity-can-uncover-the-trojan","slug":"quarantine-sparsity-can-uncover-the-trojan","title":"Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free","date":"2022-05-24","arxiv_id":"2205.11819","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/quarantine-sparsity-can-uncover-the-trojan#ran","syntology_url":"https://syntology.ai/paper/2205.11819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.11819"}},"official":{"repos":["vita-group/backdoor-lth"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/app-anytime-progressive-pruning","slug":"app-anytime-progressive-pruning","title":"APP: Anytime Progressive Pruning","date":"2022-04-04","arxiv_id":"2204.01640","repositories_listed":1,"syntology":null},{"url":"/paper/paoding-supervised-robustness-preserving-data","slug":"paoding-supervised-robustness-preserving-data","title":"Supervised Robustness-preserving Data-free Neural Network Pruning","date":"2022-04-02","arxiv_id":"2204.00783","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-networks-with-cross-layer-ranking-k","slug":"pruning-networks-with-cross-layer-ranking-k","title":"Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters","date":"2022-02-15","arxiv_id":"2202.07190","repositories_listed":1,"syntology":null},{"url":"/paper/membership-inference-attacks-and-defenses-in-1","slug":"membership-inference-attacks-and-defenses-in-1","title":"Membership Inference Attacks and Defenses in Neural Network Pruning","date":"2022-02-07","arxiv_id":"2202.03335","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-aware-sparse-regularization-for","slug":"pruning-aware-sparse-regularization-for","title":"Pruning-aware Sparse Regularization for Network Pruning","date":"2022-01-18","arxiv_id":"2201.06776","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":10,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pruning-aware-sparse-regularization-for#ran","syntology_url":"https://syntology.ai/paper/2201.06776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.06776"}},"official":{"repos":["casia-iva-lab/masksparsity"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/pruning-deep-neural-networks-generates-a","slug":"pruning-deep-neural-networks-generates-a","title":"Pruning deep neural networks generates a sparse, bio-inspired nonlinear controller for insect flight","date":"2022-01-05","arxiv_id":"2201.01852","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-the-knowledge-of-romanian-berts","slug":"distilling-the-knowledge-of-romanian-berts","title":"Distilling the Knowledge of Romanian BERTs Using Multiple Teachers","date":"2021-12-23","arxiv_id":"2112.12650","repositories_listed":1,"syntology":null},{"url":"/paper/network-compression-via-central-filter","slug":"network-compression-via-central-filter","title":"Network Compression via Central Filter","date":"2021-12-10","arxiv_id":"2112.05493","repositories_listed":1,"syntology":null},{"url":"/paper/aligned-structured-sparsity-learning-for","slug":"aligned-structured-sparsity-learning-for","title":"Aligned Structured Sparsity Learning for Efficient Image Super-Resolution","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dominosearch-find-layer-wise-fine-grained-n-m","slug":"dominosearch-find-layer-wise-fine-grained-n-m","title":"DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks","date":"2021-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/feature-gate-coupling-for-dynamic-network","slug":"feature-gate-coupling-for-dynamic-network","title":"Self-supervised Feature-Gate Coupling for Dynamic Network Pruning","date":"2021-11-29","arxiv_id":"2111.14302","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-neural-network-pruning-that","slug":"automatic-neural-network-pruning-that","title":"Automatic Neural Network Pruning that Efficiently Preserves the Model Accuracy","date":"2021-11-18","arxiv_id":"2111.09635","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/automatic-neural-network-pruning-that#ran","syntology_url":"https://syntology.ai/paper/2111.09635","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.09635"}},"official":{"repos":["nota-github/autobot_aaai23"],"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/neural-network-is-heterogeneous-phase-matters","slug":"neural-network-is-heterogeneous-phase-matters","title":"Neural network is heterogeneous: Phase matters more","date":"2021-11-03","arxiv_id":"2111.02014","repositories_listed":1,"syntology":null},{"url":"/paper/back-to-basics-efficient-network-compression-1","slug":"back-to-basics-efficient-network-compression-1","title":"How I Learned to Stop Worrying and Love Retraining","date":"2021-11-01","arxiv_id":"2111.00843","repositories_listed":1,"syntology":null},{"url":"/paper/rmnet-equivalently-removing-residual-1","slug":"rmnet-equivalently-removing-residual-1","title":"RMNet: Equivalently Removing Residual Connection from Networks","date":"2021-11-01","arxiv_id":"2111.00687","repositories_listed":1,"syntology":null},{"url":"/paper/abcp-automatic-block-wise-and-channel-wise","slug":"abcp-automatic-block-wise-and-channel-wise","title":"ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint Search","date":"2021-10-08","arxiv_id":"2110.03858","repositories_listed":1,"syntology":null},{"url":"/paper/learning-compact-representations-of-neural","slug":"learning-compact-representations-of-neural","title":"Learning Compact Representations of Neural Networks using DiscriminAtive Masking (DAM)","date":"2021-10-01","arxiv_id":"2110.00684","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-compact-representations-of-neural#ran","syntology_url":"https://syntology.ai/paper/2110.00684","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00684"}},"official":{"repos":["jayroxis/dam-pytorch"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/global-magnitude-pruning-with-minimum","slug":"global-magnitude-pruning-with-minimum","title":"Global Magnitude Pruning With Minimum Threshold Is All We Need","date":"2021-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/revisit-kernel-pruning-with-lottery-regulated","slug":"revisit-kernel-pruning-with-lottery-regulated","title":"Revisit Kernel Pruning with Lottery Regulated Grouped Convolutions","date":"2021-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/stabilizing-elastic-weight-consolidation","slug":"stabilizing-elastic-weight-consolidation","title":"Stabilizing Elastic Weight Consolidation method in practical ML tasks and using weight importances for neural network pruning","date":"2021-09-21","arxiv_id":"2109.10021","repositories_listed":1,"syntology":null},{"url":"/paper/comparing-rewinding-and-fine-tuning-in-neural-1","slug":"comparing-rewinding-and-fine-tuning-in-neural-1","title":"Reproducibility Study: Comparing Rewinding and Fine-tuning in Neural Network Pruning","date":"2021-09-20","arxiv_id":"2109.09670","repositories_listed":1,"syntology":null},{"url":"/paper/causal-explanation-of-convolutional-neural","slug":"causal-explanation-of-convolutional-neural","title":"Causal Explanation of Convolutional Neural Networks","date":"2021-09-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/an-information-theory-inspired-strategy-for","slug":"an-information-theory-inspired-strategy-for","title":"An Information Theory-inspired Strategy for Automatic Network Pruning","date":"2021-08-19","arxiv_id":"2108.08532","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-in-the-face-of-adversaries","slug":"pruning-in-the-face-of-adversaries","title":"Pruning in the Face of Adversaries","date":"2021-08-19","arxiv_id":"2108.08560","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-vs-xnor-net-a-comprehensive-study-on","slug":"pruning-vs-xnor-net-a-comprehensive-study-on","title":"Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices","date":"2021-08-13","arxiv_id":"2108.06128","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-neural-networks-with-interpolative","slug":"pruning-neural-networks-with-interpolative","title":"Model Preserving Compression for Neural Networks","date":"2021-07-30","arxiv_id":"2108.00065","repositories_listed":1,"syntology":null},{"url":"/paper/continual-learning-for-task-oriented-dialogue","slug":"continual-learning-for-task-oriented-dialogue","title":"Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking","date":"2021-07-17","arxiv_id":"2107.08173","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/continual-learning-for-task-oriented-dialogue#ran","syntology_url":"https://syntology.ai/paper/2107.08173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.08173"}},"official":{"repos":["siat-nlp/TPEM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/model-compression-as-constrained-optimization-2","slug":"model-compression-as-constrained-optimization-2","title":"Model compression as constrained optimization, with application to neural nets. Part V: combining compressions","date":"2021-07-09","arxiv_id":"2107.04380","repositories_listed":1,"syntology":null},{"url":"/paper/connectivity-matters-neural-network-pruning","slug":"connectivity-matters-neural-network-pruning","title":"Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity","date":"2021-07-05","arxiv_id":"2107.02306","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":0,"n_no_contract":8,"n_pointer_only":0,"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) · 4 unverified","sample_list":"/paper/connectivity-matters-neural-network-pruning#ran","syntology_url":"https://syntology.ai/paper/2107.02306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.02306"}},"official":{"repos":["avysogorets/effective-sparsity"],"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/dep-l-0-improving-l-0-based-network","slug":"dep-l-0-improving-l-0-based-network","title":"Dep-$L_0$: Improving $L_0$-based Network Sparsification via Dependency Modeling","date":"2021-06-30","arxiv_id":"2107.00070","repositories_listed":1,"syntology":null},{"url":"/paper/iterative-network-pruning-with-uncertainty","slug":"iterative-network-pruning-with-uncertainty","title":"Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification","date":"2021-06-21","arxiv_id":"2106.11197","repositories_listed":1,"syntology":null},{"url":"/paper/network-pruning-via-performance-maximization","slug":"network-pruning-via-performance-maximization","title":"Network Pruning via Performance Maximization","date":"2021-06-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/self-damaging-contrastive-learning","slug":"self-damaging-contrastive-learning","title":"Self-Damaging Contrastive Learning","date":"2021-06-06","arxiv_id":"2106.02990","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/self-damaging-contrastive-learning#ran","syntology_url":"https://syntology.ai/paper/2106.02990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02990"}},"official":{"repos":["VITA-Group/SDCLR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/1-times-n-block-pattern-for-network-sparsity","slug":"1-times-n-block-pattern-for-network-sparsity","title":"1xN Pattern for Pruning Convolutional Neural Networks","date":"2021-05-31","arxiv_id":"2105.14713","repositories_listed":1,"syntology":null},{"url":"/paper/network-pruning-that-matters-a-case-study-on-1","slug":"network-pruning-that-matters-a-case-study-on-1","title":"Network Pruning That Matters: A Case Study on Retraining Variants","date":"2021-05-07","arxiv_id":"2105.03193","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"8 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/network-pruning-that-matters-a-case-study-on-1#ran","syntology_url":"https://syntology.ai/paper/2105.03193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03193"}},"official":{"repos":["lehduong/NPTM"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/effective-sparsification-of-neural-networks","slug":"effective-sparsification-of-neural-networks","title":"Effective Sparsification of Neural Networks with Global Sparsity Constraint","date":"2021-05-03","arxiv_id":"2105.01571","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/effective-sparsification-of-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2105.01571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.01571"}},"official":{"repos":["x-zho14/ProbMask-official"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/rethinking-network-pruning-under-the-pre","slug":"rethinking-network-pruning-under-the-pre","title":"Rethinking Network Pruning -- under the Pre-train and Fine-tune Paradigm","date":"2021-04-18","arxiv_id":"2104.08682","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/rethinking-network-pruning-under-the-pre#ran","syntology_url":"https://syntology.ai/paper/2104.08682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.08682"}},"official":{"repos":["derronxu/sparsebert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficienttdnn-efficient-architecture-search","slug":"efficienttdnn-efficient-architecture-search","title":"EfficientTDNN: Efficient Architecture Search for Speaker Recognition","date":"2021-03-25","arxiv_id":"2103.13581","repositories_listed":1,"syntology":null},{"url":"/paper/lost-in-pruning-the-effects-of-pruning-neural","slug":"lost-in-pruning-the-effects-of-pruning-neural","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","date":"2021-03-04","arxiv_id":"2103.03014","repositories_listed":1,"syntology":null},{"url":"/paper/network-pruning-via-resource-reallocation","slug":"network-pruning-via-resource-reallocation","title":"Network Pruning via Resource Reallocation","date":"2021-03-02","arxiv_id":"2103.01847","repositories_listed":1,"syntology":null},{"url":"/paper/feature-selection-for-multivariate-time","slug":"feature-selection-for-multivariate-time","title":"Feature Selection for Multivariate Time Series via Network Pruning","date":"2021-02-11","arxiv_id":"2102.06024","repositories_listed":1,"syntology":null},{"url":"/paper/gnn-rl-compression-topology-aware-network","slug":"gnn-rl-compression-topology-aware-network","title":"Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning","date":"2021-02-05","arxiv_id":"2102.03214","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/gnn-rl-compression-topology-aware-network#ran","syntology_url":"https://syntology.ai/paper/2102.03214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.03214"}},"official":{"repos":["yusx-swapp/gnn-rl-model-compression"],"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/non-parametric-adaptive-network-pruning","slug":"non-parametric-adaptive-network-pruning","title":"Network Pruning using Adaptive Exemplar Filters","date":"2021-01-20","arxiv_id":"2101.07985","repositories_listed":1,"syntology":null},{"url":"/paper/max-affine-spline-insights-into-deep-network-1","slug":"max-affine-spline-insights-into-deep-network-1","title":"Max-Affine Spline Insights Into Deep Network Pruning","date":"2021-01-07","arxiv_id":"2101.02338","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-a-pruning-mechanism","slug":"an-empirical-study-of-a-pruning-mechanism","title":"An empirical study of a pruning mechanism","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neural-pruning-via-growing-regularization-1","slug":"neural-pruning-via-growing-regularization-1","title":"Neural Pruning via Growing Regularization","date":"2020-12-16","arxiv_id":"2012.09243","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/neural-pruning-via-growing-regularization-1#ran","syntology_url":"https://syntology.ai/paper/2012.09243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.09243"}},"official":{"repos":["mingsun-tse/regularization-pruning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/efficient-incorporation-of-multiple-latency","slug":"efficient-incorporation-of-multiple-latency","title":"Efficient Incorporation of Multiple Latency Targets in the Once-For-All Network","date":"2020-12-12","arxiv_id":"2012.06748","repositories_listed":1,"syntology":null},{"url":"/paper/diffprune-neural-network-pruning-with","slug":"diffprune-neural-network-pruning-with","title":"DiffPrune: Neural Network Pruning with Deterministic Approximate Binary Gates and $L_0$ Regularization","date":"2020-12-07","arxiv_id":"2012.03653","repositories_listed":1,"syntology":null},{"url":"/paper/robust-error-bounds-for-quantised-and-pruned","slug":"robust-error-bounds-for-quantised-and-pruned","title":"Robust error bounds for quantised and pruned neural networks","date":"2020-11-30","arxiv_id":"2012.00138","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-pruning-of-deep-convolutional","slug":"continuous-pruning-of-deep-convolutional","title":"Rethinking Weight Decay For Efficient Neural Network Pruning","date":"2020-11-20","arxiv_id":"2011.10520","repositories_listed":1,"syntology":null},{"url":"/paper/lean-graph-based-pruning-for-convolutional","slug":"lean-graph-based-pruning-for-convolutional","title":"LEAN: graph-based pruning for convolutional neural networks by extracting longest chains","date":"2020-11-13","arxiv_id":"2011.06923","repositories_listed":1,"syntology":null},{"url":"/paper/neuron-merging-compensating-for-pruned","slug":"neuron-merging-compensating-for-pruned","title":"Neuron Merging: Compensating for Pruned Neurons","date":"2020-10-25","arxiv_id":"2010.13160","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"3 ran (of which 1 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) · 0 unverified","sample_list":"/paper/neuron-merging-compensating-for-pruned#ran","syntology_url":"https://syntology.ai/paper/2010.13160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.13160"}},"official":{"repos":["friendshipkim/neuron-merging"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-deeper-look-at-the-layerwise-sparsity-of-1","slug":"a-deeper-look-at-the-layerwise-sparsity-of-1","title":"Layer-adaptive sparsity for the Magnitude-based Pruning","date":"2020-10-15","arxiv_id":"2010.07611","repositories_listed":1,"syntology":null},{"url":"/paper/advanced-dropout-a-model-free-methodology-for","slug":"advanced-dropout-a-model-free-methodology-for","title":"Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization","date":"2020-10-11","arxiv_id":"2010.05244","repositories_listed":1,"syntology":null},{"url":"/paper/a-gradient-flow-framework-for-analyzing","slug":"a-gradient-flow-framework-for-analyzing","title":"A Gradient Flow Framework For Analyzing Network Pruning","date":"2020-09-24","arxiv_id":"2009.11839","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/a-gradient-flow-framework-for-analyzing#ran","syntology_url":"https://syntology.ai/paper/2009.11839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.11839"}},"official":{"repos":["EkdeepSLubana/flowandprune"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/sanity-checking-pruning-methods-random","slug":"sanity-checking-pruning-methods-random","title":"Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot","date":"2020-09-22","arxiv_id":"2009.11094","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sanity-checking-pruning-methods-random#ran","syntology_url":"https://syntology.ai/paper/2009.11094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.11094"}},"official":{"repos":["JingtongSu/sanity-checking-pruning"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/orthoreg-robust-network-pruning-using","slug":"orthoreg-robust-network-pruning-using","title":"OrthoReg: Robust Network Pruning Using Orthonormality Regularization","date":"2020-09-10","arxiv_id":"2009.05014","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-sparse-dnn-models-without","slug":"accelerating-sparse-dnn-models-without","title":"Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity","date":"2020-08-29","arxiv_id":"2008.13006","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-adaptive-lasso-learning-sparse","slug":"hierarchical-adaptive-lasso-learning-sparse","title":"HALO: Learning to Prune Neural Networks with Shrinkage","date":"2020-08-24","arxiv_id":"2008.10183","repositories_listed":1,"syntology":null},{"url":"/paper/eagleeye-fast-sub-net-evaluation-for","slug":"eagleeye-fast-sub-net-evaluation-for","title":"EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning","date":"2020-07-06","arxiv_id":"2007.02491","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/eagleeye-fast-sub-net-evaluation-for#ran","syntology_url":"https://syntology.ai/paper/2007.02491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.02491"}},"official":{"repos":["anonymous47823493/EagleEye"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-diversity-based-pruning-of","slug":"understanding-diversity-based-pruning-of","title":"Statistical Mechanical Analysis of Neural Network Pruning","date":"2020-06-30","arxiv_id":"2006.16617","repositories_listed":1,"syntology":null},{"url":"/paper/espn-extremely-sparse-pruned-networks","slug":"espn-extremely-sparse-pruned-networks","title":"ESPN: Extremely Sparse Pruned Networks","date":"2020-06-28","arxiv_id":"2006.15741","repositories_listed":1,"syntology":null},{"url":"/paper/paying-more-attention-to-snapshots-of","slug":"paying-more-attention-to-snapshots-of","title":"Paying more attention to snapshots of Iterative Pruning: Improving Model Compression via Ensemble Distillation","date":"2020-06-20","arxiv_id":"2006.11487","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"4 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/paying-more-attention-to-snapshots-of#ran","syntology_url":"https://syntology.ai/paper/2006.11487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11487"}},"official":{"repos":["lehduong/kesi"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-framework-for-neural-network-pruning-using","slug":"a-framework-for-neural-network-pruning-using","title":"A Framework for Neural Network Pruning Using Gibbs Distributions","date":"2020-06-08","arxiv_id":"2006.04981","repositories_listed":1,"syntology":null},{"url":"/paper/weight-pruning-via-adaptive-sparsity-loss","slug":"weight-pruning-via-adaptive-sparsity-loss","title":"Weight Pruning via Adaptive Sparsity Loss","date":"2020-06-04","arxiv_id":"2006.02768","repositories_listed":1,"syntology":null},{"url":"/paper/shapley-value-as-principled-metric-for","slug":"shapley-value-as-principled-metric-for","title":"Shapley Value as Principled Metric for Structured Network Pruning","date":"2020-06-02","arxiv_id":"2006.01795","repositories_listed":1,"syntology":null},{"url":"/paper/micronet-for-efficient-language-modeling","slug":"micronet-for-efficient-language-modeling","title":"MicroNet for Efficient Language Modeling","date":"2020-05-16","arxiv_id":"2005.07877","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/micronet-for-efficient-language-modeling#ran","syntology_url":"https://syntology.ai/paper/2005.07877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.07877"}},"official":{"repos":["mit-han-lab/neurips-micronet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-flexible-extensible-software-framework-for","slug":"a-flexible-extensible-software-framework-for","title":"A flexible, extensible software framework for model compression based on the LC algorithm","date":"2020-05-15","arxiv_id":"2005.07786","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-sparse-training-find-efficient-sparse-1","slug":"dynamic-sparse-training-find-efficient-sparse-1","title":"Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers","date":"2020-05-14","arxiv_id":"2005.06870","repositories_listed":1,"syntology":null}],"record_sha256":"619029be6e5de86e3cc04b98a6232f4e67da3d3374474c45923852bc569800f0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}