{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/robust-network-pruning-with-sparse-entropic","title":"SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning","arxiv_id":"2310.04918","date":"2023-10-07","proceeding":null,"authors":["Lei You","Hei Victor Cheng"],"abstract":"This study addresses the challenge of inaccurate gradients in computing the empirical Fisher Information Matrix during neural network pruning. We introduce SWAP, a formulation of Entropic Wasserstein regression (EWR) for pruning, capitalizing on the geometric properties of the optimal transport problem. The ``swap'' of the commonly used linear regression with the EWR in optimization is analytically demonstrated to offer noise mitigation effects by incorporating neighborhood interpolation across data points with only marginal additional computational cost. The unique strength of SWAP is its intrinsic ability to balance noise reduction and covariance information preservation effectively. Extensive experiments performed on various networks and datasets show comparable performance of SWAP with state-of-the-art (SoTA) network pruning algorithms. Our proposed method outperforms the SoTA when the network size or the target sparsity is large, the gain is even larger with the existence of noisy gradients, possibly from noisy data, analog memory, or adversarial attacks. Notably, our proposed method achieves a gain of 6% improvement in accuracy and 8% improvement in testing loss for MobileNetV1 with less than one-fourth of the network parameters remaining.","url_abs":"https://arxiv.org/abs/2310.04918v4","url_pdf":"https://arxiv.org/pdf/2310.04918v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"robust-network-pruning-with-sparse-entropic","repo_url":"https://github.com/youlei202/entropic-wasserstein-pruning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"network-pruning","task_name":"Network Pruning"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"linear-regression","method_name":"Linear Regression"},{"method_slug":"mobilenetv1","method_name":"MobileNetV1"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.04918","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04918"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/youlei202/entropic-wasserstein-pruning","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran":4},"by_repo_kind":{"official":{"samples":5,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":5,"samples":[{"code_sha256_prefix":"2f7853ff01cbbc29","entry":"conv_bn","repo":"youlei202/entropic-wasserstein-pruning","repo_kind":"official","path":"models/mobilenet_v1_dropout.py","file_url":"https://github.com/youlei202/entropic-wasserstein-pruning/blob/HEAD/models/mobilenet_v1_dropout.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2f7853ff01cbbc29"}},{"code_sha256_prefix":"8b3498a0092c350a","entry":"conv_dw","repo":"youlei202/entropic-wasserstein-pruning","repo_kind":"official","path":"models/mobilenet_v1_dropout.py","file_url":"https://github.com/youlei202/entropic-wasserstein-pruning/blob/HEAD/models/mobilenet_v1_dropout.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8b3498a0092c350a"}},{"code_sha256_prefix":"264db1286a2b7928","entry":"mobilenet","repo":"youlei202/entropic-wasserstein-pruning","repo_kind":"official","path":"models/mobilenet.py","file_url":"https://github.com/youlei202/entropic-wasserstein-pruning/blob/HEAD/models/mobilenet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"264db1286a2b7928"}},{"code_sha256_prefix":"e7f1b8db41ce8554","entry":"mobilenet_v1_dropout","repo":"youlei202/entropic-wasserstein-pruning","repo_kind":"official","path":"models/mobilenet_v1_dropout.py","file_url":"https://github.com/youlei202/entropic-wasserstein-pruning/blob/HEAD/models/mobilenet_v1_dropout.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e7f1b8db41ce8554"}},{"code_sha256_prefix":"766de1c613646dc0","entry":"mobilenet_v2","repo":"youlei202/entropic-wasserstein-pruning","repo_kind":"official","path":"models/mobilenetv2.py","file_url":"https://github.com/youlei202/entropic-wasserstein-pruning/blob/HEAD/models/mobilenetv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"766de1c613646dc0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}