{"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-robust-influence-functions-with-flat","title":"Towards Robust Influence Functions with Flat Validation Minima","arxiv_id":"2505.19097","date":"2025-05-25","proceeding":null,"authors":["Xichen Ye","Yifan Wu","Weizhong Zhang","Cheng Jin","Yifan Chen"],"abstract":"The Influence Function (IF) is a widely used technique for assessing the impact of individual training samples on model predictions. However, existing IF methods often fail to provide reliable influence estimates in deep neural networks, particularly when applied to noisy training data. This issue does not stem from inaccuracies in parameter change estimation, which has been the primary focus of prior research, but rather from deficiencies in loss change estimation, specifically due to the sharpness of validation risk. In this work, we establish a theoretical connection between influence estimation error, validation set risk, and its sharpness, underscoring the importance of flat validation minima for accurate influence estimation. Furthermore, we introduce a novel estimation form of Influence Function specifically designed for flat validation minima. Experimental results across various tasks validate the superiority of our approach.","url_abs":"https://arxiv.org/abs/2505.19097v1","url_pdf":"https://arxiv.org/pdf/2505.19097v1.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":[],"tasks":[],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.19097","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19097"}},"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":"deterministic:regex_extraction","url":"https://github.com/Virusdoll/IF-FVM","reach":null}],"summary":{"ran":1,"ran_honours":1},"by_repo_kind":{"found_in_text":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"08ae03db05fbbf5f","entry":"ValMinima","repo":"Virusdoll/IF-FVM","repo_kind":"found_in_text","path":"influence/val_minima.py","file_url":"https://github.com/Virusdoll/IF-FVM/blob/HEAD/influence/val_minima.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":"08ae03db05fbbf5f"}},{"code_sha256_prefix":"c214152719229bcf","entry":"get_gpu_memory_usage","repo":"Virusdoll/IF-FVM","repo_kind":"found_in_text","path":"influence/val_minima.py","file_url":"https://github.com/Virusdoll/IF-FVM/blob/HEAD/influence/val_minima.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c214152719229bcf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}