{"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/enhancing-continual-relation-extraction-via","title":"Enhancing Continual Relation Extraction via Classifier Decomposition","arxiv_id":"2305.04636","date":"2023-05-08","proceeding":null,"authors":["Heming Xia","Peiyi Wang","Tianyu Liu","Binghuai Lin","Yunbo Cao","Zhifang Sui"],"abstract":"Continual relation extraction (CRE) models aim at handling emerging new relations while avoiding catastrophically forgetting old ones in the streaming data. Though improvements have been shown by previous CRE studies, most of them only adopt a vanilla strategy when models first learn representations of new relations. In this work, we point out that there exist two typical biases after training of this vanilla strategy: classifier bias and representation bias, which causes the previous knowledge that the model learned to be shaded. To alleviate those biases, we propose a simple yet effective classifier decomposition framework that splits the last FFN layer into separated previous and current classifiers, so as to maintain previous knowledge and encourage the model to learn more robust representations at this training stage. Experimental results on two standard benchmarks show that our proposed framework consistently outperforms the state-of-the-art CRE models, which indicates that the importance of the first training stage to CRE models may be underestimated. Our code is available at https://github.com/hemingkx/CDec.","url_abs":"https://arxiv.org/abs/2305.04636v1","url_pdf":"https://arxiv.org/pdf/2305.04636v1.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":"enhancing-continual-relation-extraction-via","repo_url":"https://github.com/hemingkx/cdec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"continual-relation-extraction","task_name":"Continual Relation Extraction"},{"task_slug":null,"task_name":"Relation"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.04636","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}