{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/tag-task-based-accumulated-gradients-for","title":"TAG: Task-based Accumulated Gradients for Lifelong learning","arxiv_id":"2105.05155","date":"2021-05-11","proceeding":null,"authors":["Pranshu Malviya","Balaraman Ravindran","Sarath Chandar"],"abstract":"When an agent encounters a continual stream of new tasks in the lifelong learning setting, it leverages the knowledge it gained from the earlier tasks to help learn the new tasks better. In such a scenario, identifying an efficient knowledge representation becomes a challenging problem. Most research works propose to either store a subset of examples from the past tasks in a replay buffer, dedicate a separate set of parameters to each task or penalize excessive updates over parameters by introducing a regularization term. While existing methods employ the general task-agnostic stochastic gradient descent update rule, we propose a task-aware optimizer that adapts the learning rate based on the relatedness among tasks. We utilize the directions taken by the parameters during the updates by accumulating the gradients specific to each task. These task-based accumulated gradients act as a knowledge base that is maintained and updated throughout the stream. We empirically show that our proposed adaptive learning rate not only accounts for catastrophic forgetting but also allows positive backward transfer. We also show that our method performs better than several state-of-the-art methods in lifelong learning on complex datasets with a large number of tasks.","url_abs":"https://arxiv.org/abs/2105.05155v3","url_pdf":"https://arxiv.org/pdf/2105.05155v3.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":"tag-task-based-accumulated-gradients-for","repo_url":"https://github.com/pranshu28/TAG","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":"lifelong-learning","task_name":"Lifelong learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/continual-learning-on-5-dataset-1-epoch","task":"Continual Learning","dataset":"5-dataset - 1 epoch","model":"TAG-RMSProp","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"62.59"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-cub-200-2011-20-tasks-1","task":"Continual Learning","dataset":"CUB-200-2011 (20 tasks) - 1 epoch","model":"TAG-RMSProp","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"61.58"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-cifar100-20-tasks-1","task":"Continual Learning","dataset":"Cifar100 (20 tasks) - 1 epoch","model":"TAG-RMSProp","rank_in_archive_order":1,"of":1,"metrics":{"Average Accuracy":"62.79"},"uses_additional_data":false},{"leaderboard":"/sota/continual-learning-on-mini-imagenet-20-tasks","task":"Continual Learning","dataset":"mini-Imagenet (20 tasks) - 1 epoch","model":"TAG-RMSProp","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"57.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"pranshu28/TAG","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"83a770a6c1ac36508fca495fb5f511ff502f7e1052f8d26c579d7412f220b9c9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}