{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/rule-induction-for-global-explanation-of","title":"Rule induction for global explanation of trained models","arxiv_id":"1808.09744","date":"2018-08-29","proceeding":"WS 2018 11","authors":["Madhumita Sushil","Simon Šuster","Walter Daelemans"],"abstract":"Understanding the behavior of a trained network and finding explanations for\nits outputs is important for improving the network's performance and\ngeneralization ability, and for ensuring trust in automated systems. Several\napproaches have previously been proposed to identify and visualize the most\nimportant features by analyzing a trained network. However, the relations\nbetween different features and classes are lost in most cases. We propose a\ntechnique to induce sets of if-then-else rules that capture these relations to\nglobally explain the predictions of a network. We first calculate the\nimportance of the features in the trained network. We then weigh the original\ninputs with these feature importance scores, simplify the transformed input\nspace, and finally fit a rule induction model to explain the model predictions.\nWe find that the output rule-sets can explain the predictions of a neural\nnetwork trained for 4-class text classification from the 20 newsgroups dataset\nto a macro-averaged F-score of 0.80. We make the code available at\nhttps://github.com/clips/interpret_with_rules.","url_abs":"http://arxiv.org/abs/1808.09744v1","url_pdf":"http://arxiv.org/pdf/1808.09744v1.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":"rule-induction-for-global-explanation-of","repo_url":"https://github.com/clips/interpret_with_rules","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"feature-importance","task_name":"Feature Importance"},{"task_slug":"text-classification","task_name":"Text Classification"},{"task_slug":"text-classification-1","task_name":"text-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1808.09744","atlas_url":"https://app.syntology.ai/?focus=1808.09744","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1808.09744"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1808.09744\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1808.09744"},"call":"get_concepts_for_paper(arxiv_id=\"1808.09744\")"}],"by_repo":[{"repo":"clips/interpret_with_rules","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"7bc61457d9ff47ee23a82ee330fe8df09cfd8b6940cb376f03152b102cce55db","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}