{"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/training-machine-learning-models-by","title":"Training Machine Learning Models by Regularizing their Explanations","arxiv_id":"1810.00869","date":"2018-09-29","proceeding":null,"authors":["Andrew Slavin Ross"],"abstract":"Neural networks are among the most accurate supervised learning methods in\nuse today. However, their opacity makes them difficult to trust in critical\napplications, especially when conditions in training may differ from those in\npractice. Recent efforts to develop explanations for neural networks and\nmachine learning models more generally have produced tools to shed light on the\nimplicit rules behind predictions. These tools can help us identify when models\nare right for the wrong reasons. However, they do not always scale to\nexplaining predictions for entire datasets, are not always at the right level\nof abstraction, and most importantly cannot correct the problems they reveal.\nIn this thesis, we explore the possibility of training machine learning models\n(with a particular focus on neural networks) using explanations themselves. We\nconsider approaches where models are penalized not only for making incorrect\npredictions but also for providing explanations that are either inconsistent\nwith domain knowledge or overly complex. These methods let us train models\nwhich can not only provide more interpretable rationales for their predictions\nbut also generalize better when training data is confounded or meaningfully\ndifferent from test data (even adversarially so).","url_abs":"http://arxiv.org/abs/1810.00869v1","url_pdf":"http://arxiv.org/pdf/1810.00869v1.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":"training-machine-learning-models-by","repo_url":"https://github.com/dtak/rrr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"dtak/rrr","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1703.03717"],"harvested_for_calls":[{"arxiv_id":"1703.03717","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1703.03717"},"call":"get_harvested_code_for_paper(arxiv_id=\"1703.03717\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"1f6d97724a4e9a5d83730f35953c9426f708bc21c5b21ef9b34a627946ebca92","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}