{"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/representer-point-selection-for-explaining","title":"Representer Point Selection for Explaining Deep Neural Networks","arxiv_id":"1811.09720","date":"2018-11-23","proceeding":"NeurIPS 2018 12","authors":["Chih-Kuan Yeh","Joon Sik Kim","Ian E. H. Yen","Pradeep Ravikumar"],"abstract":"We propose to explain the predictions of a deep neural network, by pointing\nto the set of what we call representer points in the training set, for a given\ntest point prediction. Specifically, we show that we can decompose the\npre-activation prediction of a neural network into a linear combination of\nactivations of training points, with the weights corresponding to what we call\nrepresenter values, which thus capture the importance of that training point on\nthe learned parameters of the network. But it provides a deeper understanding\nof the network than simply training point influence: with positive representer\nvalues corresponding to excitatory training points, and negative values\ncorresponding to inhibitory points, which as we show provides considerably more\ninsight. Our method is also much more scalable, allowing for real-time feedback\nin a manner not feasible with influence functions.","url_abs":"http://arxiv.org/abs/1811.09720v1","url_pdf":"http://arxiv.org/pdf/1811.09720v1.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":"representer-point-selection-for-explaining","repo_url":"https://github.com/chihkuanyeh/Representer_Point_Selection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.09720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.09720"}},"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/chihkuanyeh/Representer_Point_Selection","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"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":1,"samples":[{"code_sha256_prefix":"8c6b999f5a291101","entry":"to_np","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":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"8c6b999f5a291101"}},{"code_sha256_prefix":"82de0b9dd7b4fe36","entry":"softmax_np","repo":"chihkuanyeh/Representer_Point_Selection","repo_kind":"listed","path":"compute_representer_vals.py","file_url":"https://github.com/chihkuanyeh/Representer_Point_Selection/blob/HEAD/compute_representer_vals.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":"82de0b9dd7b4fe36"}},{"code_sha256_prefix":"c45b56feb4ff401d","entry":"load_data","repo":"chihkuanyeh/Representer_Point_Selection","repo_kind":"listed","path":"compute_representer_vals.py","file_url":"https://github.com/chihkuanyeh/Representer_Point_Selection/blob/HEAD/compute_representer_vals.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c45b56feb4ff401d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}