{"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/towards-meta-pruning-via-optimal-transport","title":"Towards Meta-Pruning via Optimal Transport","arxiv_id":"2402.07839","date":"2024-02-12","proceeding":null,"authors":["Alexander Theus","Olin Geimer","Friedrich Wicke","Thomas Hofmann","Sotiris Anagnostidis","Sidak Pal Singh"],"abstract":"Structural pruning of neural networks conventionally relies on identifying and discarding less important neurons, a practice often resulting in significant accuracy loss that necessitates subsequent fine-tuning efforts. This paper introduces a novel approach named Intra-Fusion, challenging this prevailing pruning paradigm. Unlike existing methods that focus on designing meaningful neuron importance metrics, Intra-Fusion redefines the overlying pruning procedure. Through utilizing the concepts of model fusion and Optimal Transport, we leverage an agnostically given importance metric to arrive at a more effective sparse model representation. Notably, our approach achieves substantial accuracy recovery without the need for resource-intensive fine-tuning, making it an efficient and promising tool for neural network compression. Additionally, we explore how fusion can be added to the pruning process to significantly decrease the training time while maintaining competitive performance. We benchmark our results for various networks on commonly used datasets such as CIFAR-10, CIFAR-100, and ImageNet. More broadly, we hope that the proposed Intra-Fusion approach invigorates exploration into a fresh alternative to the predominant compression approaches. Our code is available here: https://github.com/alexandertheus/Intra-Fusion.","url_abs":"https://arxiv.org/abs/2402.07839v2","url_pdf":"https://arxiv.org/pdf/2402.07839v2.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":"towards-meta-pruning-via-optimal-transport","repo_url":"https://github.com/alexandertheus/intra-fusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"neural-network-compression","task_name":"Neural Network Compression"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.07839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07839"}},"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/alexandertheus/intra-fusion","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5},"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":0,"samples":[{"code_sha256_prefix":"e7e2178058335c15","entry":"ResNet18","repo":"alexandertheus/intra-fusion","repo_kind":"official","path":"model_architectures/resnet.py","file_url":"https://github.com/alexandertheus/intra-fusion/blob/HEAD/model_architectures/resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7e2178058335c15"}},{"code_sha256_prefix":"cb7cde1fc11439bc","entry":"ResNet34","repo":"alexandertheus/intra-fusion","repo_kind":"official","path":"model_architectures/resnet.py","file_url":"https://github.com/alexandertheus/intra-fusion/blob/HEAD/model_architectures/resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb7cde1fc11439bc"}},{"code_sha256_prefix":"ab1427f6d3ed2c88","entry":"ResNet50","repo":"alexandertheus/intra-fusion","repo_kind":"official","path":"model_architectures/resnet.py","file_url":"https://github.com/alexandertheus/intra-fusion/blob/HEAD/model_architectures/resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ab1427f6d3ed2c88"}},{"code_sha256_prefix":"394322f92b2d2065","entry":"find_ignored_layers","repo":"alexandertheus/intra-fusion","repo_kind":"official","path":"utils.py","file_url":"https://github.com/alexandertheus/intra-fusion/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"394322f92b2d2065"}},{"code_sha256_prefix":"915b7da0362eb2b4","entry":"is_scalar","repo":"alexandertheus/intra-fusion","repo_kind":"official","path":"torch_pruning/_helpers.py","file_url":"https://github.com/alexandertheus/intra-fusion/blob/HEAD/torch_pruning/_helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"915b7da0362eb2b4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}