{"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/dynashare-dynamic-neural-networks-for-multi","title":"DYNASHARE: DYNAMIC NEURAL NETWORKS FOR MULTI-TASK LEARNING","arxiv_id":null,"date":"2021-09-29","proceeding":null,"authors":["Golara Javadi","Frederick Tung","Gabriel L. Oliveira"],"abstract":"Parameter sharing approaches for deep multi-task learning share a common intuition: for a single network to perform multiple prediction tasks, the network needs to support multiple specialized execution paths. However, previous parameter sharing approaches have relied on a static network structure for each task. In this paper, we propose to increase the capacity for a single network to support multiple tasks by radically increasing the space of possible specialized execution paths. DynaShare is a new approach to deep multi-task learning that learns from the training data a hierarchical gating policy consisting of a task-specific policy for coarse layer selection and gating units for individual input instances, which work together to determine the execution path at inference time. Experimental results on standard multi-task learning benchmark datasets demonstrate the potential of the proposed approach.","url_abs":"https://openreview.net/forum?id=-NefWT-x2xE","url_pdf":"https://openreview.net/pdf?id=-NefWT-x2xE","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":"dynashare-dynamic-neural-networks-for-multi","repo_url":"https://github.com/BorealisAI/DynaShare-MTL","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"dynamic-neural-networks","task_name":"Dynamic neural networks"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}