{"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/learn-prune-share-for-lifelong-learning","title":"Learn-Prune-Share for Lifelong Learning","arxiv_id":"2012.06956","date":"2020-12-13","proceeding":null,"authors":["Zifeng Wang","Tong Jian","Kaushik Chowdhury","Yanzhi Wang","Jennifer Dy","Stratis Ioannidis"],"abstract":"In lifelong learning, we wish to maintain and update a model (e.g., a neural network classifier) in the presence of new classification tasks that arrive sequentially. In this paper, we propose a learn-prune-share (LPS) algorithm which addresses the challenges of catastrophic forgetting, parsimony, and knowledge reuse simultaneously. LPS splits the network into task-specific partitions via an ADMM-based pruning strategy. This leads to no forgetting, while maintaining parsimony. Moreover, LPS integrates a novel selective knowledge sharing scheme into this ADMM optimization framework. This enables adaptive knowledge sharing in an end-to-end fashion. Comprehensive experimental results on two lifelong learning benchmark datasets and a challenging real-world radio frequency fingerprinting dataset are provided to demonstrate the effectiveness of our approach. Our experiments show that LPS consistently outperforms multiple state-of-the-art competitors.","url_abs":"https://arxiv.org/abs/2012.06956v1","url_pdf":"https://arxiv.org/pdf/2012.06956v1.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":"learn-prune-share-for-lifelong-learning","repo_url":"https://github.com/neu-spiral/LPSforLifelong","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"lifelong-learning","task_name":"Lifelong learning"}],"methods":[{"method_slug":"admm","method_name":"ADMM"},{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2012.06956","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}