{"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/if-influence-functions-are-the-answer-then","title":"If Influence Functions are the Answer, Then What is the Question?","arxiv_id":"2209.05364","date":"2022-09-12","proceeding":null,"authors":["Juhan Bae","Nathan Ng","Alston Lo","Marzyeh Ghassemi","Roger Grosse"],"abstract":"Influence functions efficiently estimate the effect of removing a single training data point on a model's learned parameters. While influence estimates align well with leave-one-out retraining for linear models, recent works have shown this alignment is often poor in neural networks. In this work, we investigate the specific factors that cause this discrepancy by decomposing it into five separate terms. We study the contributions of each term on a variety of architectures and datasets and how they vary with factors such as network width and training time. While practical influence function estimates may be a poor match to leave-one-out retraining for nonlinear networks, we show they are often a good approximation to a different object we term the proximal Bregman response function (PBRF). Since the PBRF can still be used to answer many of the questions motivating influence functions, such as identifying influential or mislabeled examples, our results suggest that current algorithms for influence function estimation give more informative results than previous error analyses would suggest.","url_abs":"https://arxiv.org/abs/2209.05364v1","url_pdf":"https://arxiv.org/pdf/2209.05364v1.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":"if-influence-functions-are-the-answer-then","repo_url":"https://github.com/pomonam/jax-influence","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"if-influence-functions-are-the-answer-then","repo_url":"https://github.com/alstonlo/torch-influence","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.05364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.05364"}},"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/alstonlo/torch-influence","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pomonam/jax-influence","reach":null}],"summary":{"ran_draft_wrong":1,"ran_violates":1,"ran_honours":1},"by_repo_kind":{"official":{"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":1,"samples":[{"code_sha256_prefix":"7795d93831d5b4cc","entry":"fit_model","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"7795d93831d5b4cc"}},{"code_sha256_prefix":"5fb29b5fb2627061","entry":"log_clip","repo":"pomonam/jax-influence","repo_kind":"official","path":"tests/test_influence_compute.py","file_url":"https://github.com/pomonam/jax-influence/blob/HEAD/tests/test_influence_compute.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5fb29b5fb2627061"}},{"code_sha256_prefix":"c25529963b1a2b0c","entry":"xe_loss","repo":"pomonam/jax-influence","repo_kind":"official","path":"tests/test_influence_compute.py","file_url":"https://github.com/pomonam/jax-influence/blob/HEAD/tests/test_influence_compute.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c25529963b1a2b0c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}