{"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":"/method/pruning/papers/33","list_of":"/method/pruning","method":"Pruning","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":33,"pages_in_order":39,"rows_per_page":100,"rows":[3201,3300],"of":3874,"counts":{"archive_papers_tagged":3874,"with_a_code_link":1508,"where_syntology_ran_a_sample":478,"not_listed_spam_title":0,"listed":3874,"listed_where_code_ran":478,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":395,"every_run_a_failure_of_syntologys_instrument":83,"listed_with_a_run_with_no_instrument_failure":395,"listed_every_run_a_failure_of_syntologys_instrument":83,"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":"/method/pruning","prev":"/method/pruning/papers/32","next":"/method/pruning/papers/34","papers":[{"paper":"/paper/dmcp-differentiable-markov-channel-pruning","slug":"dmcp-differentiable-markov-channel-pruning","title":"DMCP: Differentiable Markov Channel Pruning for Neural Networks","date":"2020-05-07","arxiv_id":"2005.03354","n_code_links":1,"syntology":null},{"paper":null,"slug":"dependency-aware-filter-pruning","title":"Dependency Aware Filter Pruning","date":"2020-05-06","arxiv_id":"2005.02634","n_code_links":0,"syntology":null},{"paper":null,"slug":"noise-pollution-in-hospital-readmission","title":"Noise Pollution in Hospital Readmission Prediction: Long Document Classification with Reinforcement Learning","date":"2020-05-04","arxiv_id":"2005.01259","n_code_links":0,"syntology":null},{"paper":null,"slug":"successfully-applying-the-stabilized-lottery","title":"Successfully Applying the Stabilized Lottery Ticket Hypothesis to the Transformer Architecture","date":"2020-05-04","arxiv_id":"2005.03454","n_code_links":0,"syntology":null},{"paper":null,"slug":"svm-lattice-a-recognition-evaluation-frame","title":"SVM-Lattice: A Recognition & Evaluation Frame for Double-peaked Profiles","date":"2020-05-02","arxiv_id":"2005.00678","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluation-dataset-and-methodology-for","title":"Evaluation Dataset and Methodology for Extracting Application-Specific Taxonomies from the Wikipedia Knowledge Graph","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"probabilistic-connection-importance-inference","title":"Probabilistic Connection Importance Inference and Lossless Compression of Deep Neural Networks","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pruned-graph-scattering-transforms","title":"Pruned Graph Scattering Transforms","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/tapaco-a-corpus-of-sentential-paraphrases-for","slug":"tapaco-a-corpus-of-sentential-paraphrases-for","title":"TaPaCo: A Corpus of Sentential Paraphrases for 73 Languages","date":"2020-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"when-bert-plays-the-lottery-all-tickets-are","title":"When BERT Plays the Lottery, All Tickets Are Winning","date":"2020-05-01","arxiv_id":"2005.00561","n_code_links":0,"syntology":null},{"paper":"/paper/how-do-decisions-emerge-across-layers-in","slug":"how-do-decisions-emerge-across-layers-in","title":"How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking","date":"2020-04-30","arxiv_id":"2004.14992","n_code_links":2,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"6 ran (of which 4 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) · 4 unverified","official":{"repos":["nicola-decao/diffmask"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"out-of-the-box-channel-pruned-networks","title":"Out-of-the-box channel pruned networks","date":"2020-04-30","arxiv_id":"2004.14584","n_code_links":0,"syntology":null},{"paper":null,"slug":"piecewise-digital-predistortion-fo-mmwave","title":"Piecewise Digital Predistortion fo mmWave Active Antenna Arrays: Algorithms and Measurements","date":"2020-04-30","arxiv_id":"2003.06348","n_code_links":0,"syntology":null},{"paper":"/paper/pruning-artificial-neural-networks-a-way-to","slug":"pruning-artificial-neural-networks-a-way-to","title":"Pruning artificial neural networks: a way to find well-generalizing, high-entropy sharp minima","date":"2020-04-30","arxiv_id":"2004.14765","n_code_links":4,"syntology":null},{"paper":"/paper/trp-trained-rank-pruning-for-efficient-deep","slug":"trp-trained-rank-pruning-for-efficient-deep","title":"TRP: Trained Rank Pruning for Efficient Deep Neural Networks","date":"2020-04-30","arxiv_id":"2004.14566","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/expansion-via-prediction-of-importance-with","slug":"expansion-via-prediction-of-importance-with","title":"Expansion via Prediction of Importance with Contextualization","date":"2020-04-29","arxiv_id":"2004.14245","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-class-discrimination-based-cnn","title":"Rethinking Class-Discrimination Based CNN Channel Pruning","date":"2020-04-29","arxiv_id":"2004.14492","n_code_links":0,"syntology":null},{"paper":"/paper/woodfisher-efficient-second-order","slug":"woodfisher-efficient-second-order","title":"WoodFisher: Efficient Second-Order Approximation for Neural Network Compression","date":"2020-04-29","arxiv_id":"2004.14340","n_code_links":1,"syntology":null},{"paper":null,"slug":"streamlining-tensor-and-network-pruning-in","title":"Streamlining Tensor and Network Pruning in PyTorch","date":"2020-04-28","arxiv_id":"2004.13770","n_code_links":0,"syntology":null},{"paper":null,"slug":"flexsa-flexible-systolic-array-architecture","title":"FlexSA: Flexible Systolic Array Architecture for Efficient Pruned DNN Model Training","date":"2020-04-27","arxiv_id":"2004.13027","n_code_links":0,"syntology":null},{"paper":"/paper/dgd-densifying-the-knowledge-of-neural","slug":"dgd-densifying-the-knowledge-of-neural","title":"Filter Grafting for Deep Neural Networks: Reason, Method, and Cultivation","date":"2020-04-26","arxiv_id":"2004.12311","n_code_links":1,"syntology":null},{"paper":"/paper/relational-graph-attention-network-for-aspect","slug":"relational-graph-attention-network-for-aspect","title":"Relational Graph Attention Network for Aspect-based Sentiment Analysis","date":"2020-04-26","arxiv_id":"2004.12362","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["shenwzh3/RGAT-ABSA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/convolution-weight-distribution-assumption","slug":"convolution-weight-distribution-assumption","title":"Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning","date":"2020-04-24","arxiv_id":"2004.11627","n_code_links":0,"syntology":{"ran":3,"of":7,"n_ran_checked":1,"n_instrument":2,"unverified":4,"pointer_only":2,"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) · 4 unverified","official":null}},{"paper":"/paper/lite-transformer-with-long-short-range","slug":"lite-transformer-with-long-short-range","title":"Lite Transformer with Long-Short Range Attention","date":"2020-04-24","arxiv_id":"2004.11886","n_code_links":2,"syntology":null},{"paper":"/paper/on-sparsifying-encoder-outputs-in-sequence-to","slug":"on-sparsifying-encoder-outputs-in-sequence-to","title":"On Sparsifying Encoder Outputs in Sequence-to-Sequence Models","date":"2020-04-24","arxiv_id":"2004.11854","n_code_links":1,"syntology":null},{"paper":"/paper/sipa-a-simple-framework-for-efficient","slug":"sipa-a-simple-framework-for-efficient","title":"SIPA: A Simple Framework for Efficient Networks","date":"2020-04-24","arxiv_id":"2004.14476","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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","official":{"repos":["Lee-Gihun/MicroNet_OSI-AI"],"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"]}}},{"paper":null,"slug":"towards-real-time-dnn-inference-on-mobile","title":"Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization","date":"2020-04-22","arxiv_id":"2004.11250","n_code_links":0,"syntology":null},{"paper":"/paper/learning-low-rank-deep-neural-networks-via","slug":"learning-low-rank-deep-neural-networks-via","title":"Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification","date":"2020-04-20","arxiv_id":"2004.09031","n_code_links":1,"syntology":null},{"paper":"/paper/finding-the-optimal-network-depth-in","slug":"finding-the-optimal-network-depth-in","title":"Finding the Optimal Network Depth in Classification Tasks","date":"2020-04-17","arxiv_id":"2004.08172","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-unified-dnn-weight-compression-framework","title":"A Unified DNN Weight Compression Framework Using Reweighted Optimization Methods","date":"2020-04-12","arxiv_id":"2004.05531","n_code_links":0,"syntology":null},{"paper":"/paper/blind-adversarial-pruning-balance-accuracy","slug":"blind-adversarial-pruning-balance-accuracy","title":"Blind Adversarial Pruning: Balance Accuracy, Efficiency and Robustness","date":"2020-04-10","arxiv_id":"2004.05913","n_code_links":1,"syntology":null},{"paper":null,"slug":"prune2edge-a-multi-phase-pruning-pipelines-to","title":"Prune2Edge: A Multi-Phase Pruning Pipelines to Deep Ensemble Learning in IIoT","date":"2020-04-09","arxiv_id":"2004.04710","n_code_links":0,"syntology":null},{"paper":"/paper/poor-man-s-bert-smaller-and-faster","slug":"poor-man-s-bert-smaller-and-faster","title":"On the Effect of Dropping Layers of Pre-trained Transformer Models","date":"2020-04-08","arxiv_id":"2004.03844","n_code_links":4,"syntology":{"ran":7,"of":8,"n_ran_checked":4,"n_instrument":3,"unverified":1,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["hsajjad/transformers"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"gradient-based-training-and-pruning-of-radial","title":"Gradient-Based Training and Pruning of Radial Basis Function Networks with an Application in Materials Physics","date":"2020-04-06","arxiv_id":"2004.02569","n_code_links":0,"syntology":null},{"paper":"/paper/network-adjustment-channel-search-guided-by","slug":"network-adjustment-channel-search-guided-by","title":"Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio","date":"2020-04-06","arxiv_id":"2004.02767","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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","official":{"repos":["danczs/NetworkAdjustment"],"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"]}}},{"paper":"/paper/dsa-more-efficient-budgeted-pruning-via","slug":"dsa-more-efficient-budgeted-pruning-via","title":"DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation","date":"2020-04-05","arxiv_id":"2004.02164","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"composition-of-saliency-metrics-for-channel","title":"Composition of Saliency Metrics for Channel Pruning with a Myopic Oracle","date":"2020-04-03","arxiv_id":"2004.03376","n_code_links":0,"syntology":null},{"paper":"/paper/dhp-differentiable-meta-pruning-via","slug":"dhp-differentiable-meta-pruning-via","title":"DHP: Differentiable Meta Pruning via HyperNetworks","date":"2020-03-30","arxiv_id":"2003.13683","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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","official":{"repos":["ofsoundof/dhp"],"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"]}}},{"paper":"/paper/how-not-to-give-a-flop-combining","slug":"how-not-to-give-a-flop-combining","title":"How Not to Give a FLOP: Combining Regularization and Pruning for Efficient Inference","date":"2020-03-30","arxiv_id":"2003.13593","n_code_links":1,"syntology":null},{"paper":null,"slug":"da-nas-data-adapted-pruning-for-efficient","title":"DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search","date":"2020-03-27","arxiv_id":"2003.12563","n_code_links":0,"syntology":null},{"paper":"/paper/data-parallelism-in-training-sparse-neural","slug":"data-parallelism-in-training-sparse-neural","title":"Understanding the Effects of Data Parallelism and Sparsity on Neural Network Training","date":"2020-03-25","arxiv_id":"2003.11316","n_code_links":0,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":null}},{"paper":"/paper/born-again-tree-ensembles","slug":"born-again-tree-ensembles","title":"Born-Again Tree Ensembles","date":"2020-03-24","arxiv_id":"2003.11132","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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","official":{"repos":["vidalt/BA-Trees"],"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"]}}},{"paper":"/paper/group-sparsity-the-hinge-between-filter","slug":"group-sparsity-the-hinge-between-filter","title":"Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression","date":"2020-03-19","arxiv_id":"2003.08935","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"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","official":{"repos":["ofsoundof/group_sparsity"],"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"]}}},{"paper":"/paper/tf-coder-program-synthesis-for-tensor","slug":"tf-coder-program-synthesis-for-tensor","title":"TF-Coder: Program Synthesis for Tensor Manipulations","date":"2020-03-19","arxiv_id":"2003.09040","n_code_links":2,"syntology":{"ran":8,"of":14,"n_ran_checked":8,"n_instrument":0,"unverified":6,"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) · 6 unverified","official":{"repos":["google-research/tensorflow-coder"],"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":["listed","official"]}}},{"paper":null,"slug":"graph-attention-network-based-pruning-for","title":"Graph Attention Network based Pruning for Reconstructing 3D Liver Vessel Morphology from Contrasted CT Images","date":"2020-03-18","arxiv_id":"2003.07999","n_code_links":0,"syntology":null},{"paper":null,"slug":"mint-deep-network-compression-via-mutual","title":"MINT: Deep Network Compression via Mutual Information-based Neuron Trimming","date":"2020-03-18","arxiv_id":"2003.08472","n_code_links":0,"syntology":null},{"paper":null,"slug":"verification-of-neural-networks-enhancing","title":"Verification of Neural Networks: Enhancing Scalability through Pruning","date":"2020-03-17","arxiv_id":"2003.07636","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-automatic-attribute-based-access-control","title":"An Automatic Attribute Based Access Control Policy Extraction from Access Logs","date":"2020-03-16","arxiv_id":"2003.07270","n_code_links":0,"syntology":null},{"paper":null,"slug":"channel-pruning-guided-by-classification-loss","title":"Channel Pruning Guided by Classification Loss and Feature Importance","date":"2020-03-15","arxiv_id":"2003.06757","n_code_links":0,"syntology":null},{"paper":null,"slug":"cocopie-making-mobile-ai-sweet-as-pie","title":"CoCoPIE: Making Mobile AI Sweet As PIE --Compression-Compilation Co-Design Goes a Long Way","date":"2020-03-14","arxiv_id":"2003.06700","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-privacy-preserving-dnn-pruning-and-mobile","title":"A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework","date":"2020-03-13","arxiv_id":"2003.06513","n_code_links":0,"syntology":null},{"paper":null,"slug":"edge-tailored-perception-fast-inferencing-in","title":"LCP: A Low-Communication Parallelization Method for Fast Neural Network Inference in Image Recognition","date":"2020-03-13","arxiv_id":"2003.06464","n_code_links":0,"syntology":null},{"paper":null,"slug":"when-are-non-parametric-methods-robust","title":"When are Non-Parametric Methods Robust?","date":"2020-03-13","arxiv_id":"2003.06121","n_code_links":0,"syntology":null},{"paper":null,"slug":"sasl-saliency-adaptive-sparsity-learning-for","title":"SASL: Saliency-Adaptive Sparsity Learning for Neural Network Acceleration","date":"2020-03-12","arxiv_id":"2003.05891","n_code_links":0,"syntology":null},{"paper":null,"slug":"kernel-quantization-for-efficient-network","title":"Kernel Quantization for Efficient Network Compression","date":"2020-03-11","arxiv_id":"2003.05148","n_code_links":0,"syntology":null},{"paper":"/paper/ap-mtl-attention-pruned-multi-task-learning","slug":"ap-mtl-attention-pruned-multi-task-learning","title":"AP-MTL: Attention Pruned Multi-task Learning Model for Real-time Instrument Detection and Segmentation in Robot-assisted Surgery","date":"2020-03-10","arxiv_id":"2003.04769","n_code_links":1,"syntology":null},{"paper":"/paper/channel-pruning-via-optimal-thresholding","slug":"channel-pruning-via-optimal-thresholding","title":"Channel Pruning via Optimal Thresholding","date":"2020-03-10","arxiv_id":"2003.04566","n_code_links":1,"syntology":null},{"paper":"/paper/neural-networks-are-surprisingly-modular","slug":"neural-networks-are-surprisingly-modular","title":"Pruned Neural Networks are Surprisingly Modular","date":"2020-03-10","arxiv_id":"2003.04881","n_code_links":1,"syntology":null},{"paper":"/paper/towards-practical-lottery-ticket-hypothesis","slug":"towards-practical-lottery-ticket-hypothesis","title":"Towards Practical Lottery Ticket Hypothesis for Adversarial Training","date":"2020-03-06","arxiv_id":"2003.05733","n_code_links":1,"syntology":null},{"paper":"/paper/what-is-the-state-of-neural-network-pruning","slug":"what-is-the-state-of-neural-network-pruning","title":"What is the State of Neural Network Pruning?","date":"2020-03-06","arxiv_id":"2003.03033","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":11,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["jjgo/shrinkbench"],"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"]}}},{"paper":"/paper/adaptive-neural-connections-for-sparsity","slug":"adaptive-neural-connections-for-sparsity","title":"Adaptive Neural Connections for Sparsity Learning","date":"2020-03-05","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-as-a-teacher-contextual-embeddings-for","title":"BERT as a Teacher: Contextual Embeddings for Sequence-Level Reward","date":"2020-03-05","arxiv_id":"2003.02738","n_code_links":0,"syntology":null},{"paper":null,"slug":"cluster-pruning-an-efficient-filter-pruning","title":"Cluster Pruning: An Efficient Filter Pruning Method for Edge AI Vision Applications","date":"2020-03-05","arxiv_id":"2003.02449","n_code_links":0,"syntology":null},{"paper":"/paper/comparing-rewinding-and-fine-tuning-in-neural","slug":"comparing-rewinding-and-fine-tuning-in-neural","title":"Comparing Rewinding and Fine-tuning in Neural Network Pruning","date":"2020-03-05","arxiv_id":"2003.02389","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":2,"n_instrument":4,"unverified":0,"pointer_only":6,"phrase":"6 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; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lottery-ticket/rewinding-iclr20-public"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pruning-filters-while-training-for","title":"Pruning Filters while Training for Efficiently Optimizing Deep Learning Networks","date":"2020-03-05","arxiv_id":"2003.02800","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-joint-transmission-recognition-for-power","title":"Joint Device-Edge Inference over Wireless Links with Pruning","date":"2020-03-04","arxiv_id":"2003.02027","n_code_links":0,"syntology":null},{"paper":null,"slug":"privacy-preserving-learning-via-deep-net","title":"Privacy-preserving Learning via Deep Net Pruning","date":"2020-03-04","arxiv_id":"2003.01876","n_code_links":0,"syntology":null},{"paper":"/paper/good-subnetworks-provably-exist-pruning-via","slug":"good-subnetworks-provably-exist-pruning-via","title":"Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection","date":"2020-03-03","arxiv_id":"2003.01794","n_code_links":1,"syntology":{"ran":4,"of":7,"n_ran_checked":2,"n_instrument":2,"unverified":3,"pointer_only":7,"phrase":"4 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["lushleaf/Network-Pruning-Greedy-Forward-Selection"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"energy-efficient-and-robust-cumulative","title":"Energy-efficient and Robust Cumulative Training with Net2Net Transformation","date":"2020-03-02","arxiv_id":"2003.01204","n_code_links":0,"syntology":null},{"paper":null,"slug":"mbgd-rda-training-and-similarity-based-rule","title":"MBGD-RDA Training and Rule Pruning for Concise TSK Fuzzy Regression Models","date":"2020-03-01","arxiv_id":"2003.00608","n_code_links":0,"syntology":null},{"paper":null,"slug":"learned-threshold-pruning","title":"Learned Threshold Pruning","date":"2020-02-28","arxiv_id":"2003.00075","n_code_links":0,"syntology":null},{"paper":"/paper/train-large-then-compress-rethinking-model","slug":"train-large-then-compress-rethinking-model","title":"Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers","date":"2020-02-26","arxiv_id":"2002.11794","n_code_links":2,"syntology":null},{"paper":"/paper/sparsity-promoting-algorithms-for-the","slug":"sparsity-promoting-algorithms-for-the","title":"Sparsity-promoting algorithms for the discovery of informative Koopman invariant subspaces","date":"2020-02-25","arxiv_id":"2002.10637","n_code_links":1,"syntology":null},{"paper":"/paper/hrank-filter-pruning-using-high-rank-feature","slug":"hrank-filter-pruning-using-high-rank-feature","title":"HRank: Filter Pruning using High-Rank Feature Map","date":"2020-02-24","arxiv_id":"2002.10179","n_code_links":2,"syntology":null},{"paper":"/paper/on-pruning-adversarially-robust-neural","slug":"on-pruning-adversarially-robust-neural","title":"HYDRA: Pruning Adversarially Robust Neural Networks","date":"2020-02-24","arxiv_id":"2002.10509","n_code_links":4,"syntology":{"ran":4,"of":19,"n_ran_checked":4,"n_instrument":0,"unverified":15,"pointer_only":17,"phrase":"4 ran (of which 4 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) · 15 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["inspire-group/compactness-robustness"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/gradual-channel-pruning-while-training-using","slug":"gradual-channel-pruning-while-training-using","title":"Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural Networks","date":"2020-02-23","arxiv_id":"2002.09958","n_code_links":1,"syntology":null},{"paper":null,"slug":"poet-bin-power-efficient-tiny-binary-neurons","title":"PoET-BiN: Power Efficient Tiny Binary Neurons","date":"2020-02-23","arxiv_id":"2002.09794","n_code_links":0,"syntology":null},{"paper":null,"slug":"performance-aware-convolutional-neural","title":"Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs","date":"2020-02-20","arxiv_id":"2002.08697","n_code_links":0,"syntology":null},{"paper":"/paper/compressing-bert-studying-the-effects-of-1","slug":"compressing-bert-studying-the-effects-of-1","title":"Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning","date":"2020-02-19","arxiv_id":"2002.08307","n_code_links":1,"syntology":null},{"paper":"/paper/knapsack-pruning-with-inner-distillation","slug":"knapsack-pruning-with-inner-distillation","title":"Knapsack Pruning with Inner Distillation","date":"2020-02-19","arxiv_id":"2002.08258","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["yoniaflalo/knapsack_pruning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pruning-untrained-neural-networks-principles","title":"Robust Pruning at Initialization","date":"2020-02-19","arxiv_id":"2002.08797","n_code_links":0,"syntology":null},{"paper":null,"slug":"rtmobile-beyond-real-time-mobile-acceleration","title":"RTMobile: Beyond Real-Time Mobile Acceleration of RNNs for Speech Recognition","date":"2020-02-19","arxiv_id":"2002.11474","n_code_links":0,"syntology":null},{"paper":null,"slug":"block-switching-a-stochastic-approach-for","title":"Block Switching: A Stochastic Approach for Deep Learning Security","date":"2020-02-18","arxiv_id":"2002.07920","n_code_links":0,"syntology":null},{"paper":"/paper/picking-winning-tickets-before-training-by-1","slug":"picking-winning-tickets-before-training-by-1","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","date":"2020-02-18","arxiv_id":"2002.07376","n_code_links":3,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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","official":{"repos":["alecwangcq/GraSP"],"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"]}}},{"paper":"/paper/identifying-critical-neurons-in-ann","slug":"identifying-critical-neurons-in-ann","title":"Identifying Critical Neurons in ANN Architectures using Mixed Integer Programming","date":"2020-02-17","arxiv_id":"2002.07259","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-reliability-of-latent-dirichlet","title":"Improving Reliability of Latent Dirichlet Allocation by Assessing Its Stability Using Clustering Techniques on Replicated Runs","date":"2020-02-14","arxiv_id":"2003.04980","n_code_links":0,"syntology":null},{"paper":"/paper/layer-wise-pruning-and-auto-tuning-of-layer","slug":"layer-wise-pruning-and-auto-tuning-of-layer","title":"AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks","date":"2020-02-14","arxiv_id":"2002.06048","n_code_links":1,"syntology":null},{"paper":"/paper/lookahead-a-far-sighted-alternative-of-1","slug":"lookahead-a-far-sighted-alternative-of-1","title":"Lookahead: a Far-Sighted Alternative of Magnitude-based Pruning","date":"2020-02-12","arxiv_id":"2002.04809","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 6 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alinlab/lookahead_pruning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"retrain-or-not-retrain-efficient-pruning","title":"Retrain or not retrain? -- efficient pruning methods of deep CNN networks","date":"2020-02-12","arxiv_id":"2002.07051","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-of-local-optima-for-learning-feature","title":"A study of local optima for learning feature interactions using neural networks","date":"2020-02-11","arxiv_id":"2002.04322","n_code_links":0,"syntology":null},{"paper":null,"slug":"exact-indexing-of-time-series-under-dynamic","title":"Exact Indexing of Time Series under Dynamic Time Warping","date":"2020-02-11","arxiv_id":"2002.04187","n_code_links":0,"syntology":null},{"paper":null,"slug":"pcnn-pattern-based-fine-grained-regular","title":"PCNN: Pattern-based Fine-Grained Regular Pruning towards Optimizing CNN Accelerators","date":"2020-02-11","arxiv_id":"2002.04997","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-efficient-network-architecture-and","title":"Network Pruning via Annealing and Direct Sparsity Control","date":"2020-02-11","arxiv_id":"2002.04301","n_code_links":0,"syntology":null},{"paper":null,"slug":"convolutional-neural-network-pruning-using","title":"Convolutional Neural Network Pruning Using Filter Attenuation","date":"2020-02-09","arxiv_id":"2002.03299","n_code_links":0,"syntology":null},{"paper":null,"slug":"index-based-solutions-for-efficient-density","title":"Index-based Solutions for Efficient Density Peak Clustering","date":"2020-02-08","arxiv_id":"2002.03182","n_code_links":0,"syntology":null},{"paper":"/paper/soft-threshold-weight-reparameterization-for","slug":"soft-threshold-weight-reparameterization-for","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","date":"2020-02-08","arxiv_id":"2002.03231","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"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) · 2 unverified","official":{"repos":["RAIVNLab/STR"],"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"]}}},{"paper":null,"slug":"activation-density-driven-energy-efficient","title":"Activation Density driven Energy-Efficient Pruning in Training","date":"2020-02-07","arxiv_id":"2002.02949","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-pruning-for-quantized-neural","title":"Automatic Pruning for Quantized Neural Networks","date":"2020-02-03","arxiv_id":"2002.00523","n_code_links":0,"syntology":null},{"paper":"/paper/distance-metric-learning-for-graph-structured","slug":"distance-metric-learning-for-graph-structured","title":"Distance Metric Learning for Graph Structured Data","date":"2020-02-03","arxiv_id":"2002.00727","n_code_links":2,"syntology":null},{"paper":null,"slug":"minimum-length-scheduling-for-full-duplex","title":"Minimum Length Scheduling for Full Duplex Time-Critical Wireless Powered Communication Networks","date":"2020-02-03","arxiv_id":"2002.00586","n_code_links":0,"syntology":null}],"record_sha256":"347be5a66a04be708861fae5eddbf07acaae518e600c800e8dfab9a98aec85e4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}