{"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/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":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}