{"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/efficient-multi-task-auxiliary-learning","title":"Efficient Multi-Task Auxiliary Learning: Selecting Auxiliary Data by Feature Similarity","arxiv_id":null,"date":"2021-11-01","proceeding":"EMNLP 2021 11","authors":["Po-Nien Kung","Sheng-Siang Yin","Yi-Cheng Chen","Tse-Hsuan Yang","Yun-Nung Chen"],"abstract":"Multi-task auxiliary learning utilizes a set of relevant auxiliary tasks to improve the performance of a primary task. A common usage is to manually select multiple auxiliary tasks for multi-task learning on all data, which raises two issues: (1) selecting beneficial auxiliary tasks for a primary task is nontrivial; (2) when the auxiliary datasets are large, training on all data becomes time-expensive and impractical. Therefore, this paper focuses on addressing these problems and proposes a time-efficient sampling method to select the data that is most relevant to the primary task. The proposed method allows us to only train on the most beneficial sub-datasets from the auxiliary tasks, achieving efficient multi-task auxiliary learning. The experiments on three benchmark datasets (RTE, MRPC, STS-B) show that our method significantly outperforms random sampling and ST-DNN. Also, by applying our method, the model can surpass fully-trained MT-DNN on RTE, MRPC, STS-B, using only 50%, 66%, and 1% of data, respectively.","url_abs":"https://aclanthology.org/2021.emnlp-main.34","url_pdf":"https://aclanthology.org/2021.emnlp-main.34.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":"efficient-multi-task-auxiliary-learning","repo_url":"https://github.com/miulab/fastmtl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"auxiliary-learning","task_name":"Auxiliary Learning"},{"task_slug":null,"task_name":"MRPC"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"rte","task_name":"RTE"},{"task_slug":"sts","task_name":"STS"},{"task_slug":null,"task_name":"STS-B"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}