{"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/re-basin-via-implicit-sinkhorn","title":"Re-basin via implicit Sinkhorn differentiation","arxiv_id":"2212.12042","date":"2022-12-22","proceeding":"CVPR 2023 1","authors":["Fidel A. Guerrero Peña","Heitor Rapela Medeiros","Thomas Dubail","Masih Aminbeidokhti","Eric Granger","Marco Pedersoli"],"abstract":"The recent emergence of new algorithms for permuting models into functionally equivalent regions of the solution space has shed some light on the complexity of error surfaces, and some promising properties like mode connectivity. However, finding the right permutation is challenging, and current optimization techniques are not differentiable, which makes it difficult to integrate into a gradient-based optimization, and often leads to sub-optimal solutions. In this paper, we propose a Sinkhorn re-basin network with the ability to obtain the transportation plan that better suits a given objective. Unlike the current state-of-art, our method is differentiable and, therefore, easy to adapt to any task within the deep learning domain. Furthermore, we show the advantage of our re-basin method by proposing a new cost function that allows performing incremental learning by exploiting the linear mode connectivity property. The benefit of our method is compared against similar approaches from the literature, under several conditions for both optimal transport finding and linear mode connectivity. The effectiveness of our continual learning method based on re-basin is also shown for several common benchmark datasets, providing experimental results that are competitive with state-of-art results from the literature.","url_abs":"https://arxiv.org/abs/2212.12042v1","url_pdf":"https://arxiv.org/pdf/2212.12042v1.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":"re-basin-via-implicit-sinkhorn","repo_url":"https://github.com/fagp/sinkhorn-rebasin","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"linear-mode-connectivity","task_name":"Linear Mode Connectivity"},{"task_slug":"models-alignment","task_name":"Models Alignment"},{"task_slug":"re-basin","task_name":"Re-basin"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.12042","atlas_url":"https://app.syntology.ai/?focus=2212.12042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.12042"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/fagp/sinkhorn-rebasin","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"29a3c19f36add85c","entry":"matching","repo":"fagp/sinkhorn-rebasin","repo_kind":"official","path":"rebasin/rebasinnet/sinkhorn.py","file_url":"https://github.com/fagp/sinkhorn-rebasin/blob/HEAD/rebasin/rebasinnet/sinkhorn.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"29a3c19f36add85c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}