{"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/complement-objective-training","title":"Complement Objective Training","arxiv_id":"1903.01182","date":"2019-03-04","proceeding":"ICLR 2019 5","authors":["Hao-Yun Chen","Pei-Hsin Wang","Chun-Hao Liu","Shih-Chieh Chang","Jia-Yu Pan","Yu-Ting Chen","Wei Wei","Da-Cheng Juan"],"abstract":"Learning with a primary objective, such as softmax cross entropy for\nclassification and sequence generation, has been the norm for training deep\nneural networks for years. Although being a widely-adopted approach, using\ncross entropy as the primary objective exploits mostly the information from the\nground-truth class for maximizing data likelihood, and largely ignores\ninformation from the complement (incorrect) classes. We argue that, in addition\nto the primary objective, training also using a complement objective that\nleverages information from the complement classes can be effective in improving\nmodel performance. This motivates us to study a new training paradigm that\nmaximizes the likelihood of the groundtruth class while neutralizing the\nprobabilities of the complement classes. We conduct extensive experiments on\nmultiple tasks ranging from computer vision to natural language understanding.\nThe experimental results confirm that, compared to the conventional training\nwith just one primary objective, training also with the complement objective\nfurther improves the performance of the state-of-the-art models across all\ntasks. In addition to the accuracy improvement, we also show that models\ntrained with both primary and complement objectives are more robust to\nsingle-step adversarial attacks.","url_abs":"http://arxiv.org/abs/1903.01182v2","url_pdf":"http://arxiv.org/pdf/1903.01182v2.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":"complement-objective-training","repo_url":"https://github.com/henry8527/COT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.01182","atlas_url":"https://app.syntology.ai/?focus=1903.01182","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":"1903.01182"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1903.01182\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1903.01182"},"call":"get_concepts_for_paper(arxiv_id=\"1903.01182\")"}],"by_repo":[{"repo":"henry8527/COT","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":"441b1e6a11d7627d59069257b10fe7fd9f34fa492ba053817365f2fc85a2727a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}