{"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/i2i-initializing-adapters-with-improvised","title":"I2I: Initializing Adapters with Improvised Knowledge","arxiv_id":"2304.02168","date":"2023-04-04","proceeding":null,"authors":["Tejas Srinivasan","Furong Jia","Mohammad Rostami","Jesse Thomason"],"abstract":"Adapters present a promising solution to the catastrophic forgetting problem in continual learning. However, training independent Adapter modules for every new task misses an opportunity for cross-task knowledge transfer. We propose Improvise to Initialize (I2I), a continual learning algorithm that initializes Adapters for incoming tasks by distilling knowledge from previously-learned tasks' Adapters. We evaluate I2I on CLiMB, a multimodal continual learning benchmark, by conducting experiments on sequences of visual question answering tasks. Adapters trained with I2I consistently achieve better task accuracy than independently-trained Adapters, demonstrating that our algorithm facilitates knowledge transfer between task Adapters. I2I also results in better cross-task knowledge transfer than the state-of-the-art AdapterFusion without incurring the associated parametric cost.","url_abs":"https://arxiv.org/abs/2304.02168v2","url_pdf":"https://arxiv.org/pdf/2304.02168v2.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":"i2i-initializing-adapters-with-improvised","repo_url":"https://github.com/glamor-usc/climb","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.02168","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}