{"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/improving-task-free-continual-learning-by","title":"Improving Task-free Continual Learning by Distributionally Robust Memory Evolution","arxiv_id":"2207.07256","date":"2022-07-15","proceeding":null,"authors":["Zhenyi Wang","Li Shen","Le Fang","Qiuling Suo","Tiehang Duan","Mingchen Gao"],"abstract":"Task-free continual learning (CL) aims to learn a non-stationary data stream without explicit task definitions and not forget previous knowledge. The widely adopted memory replay approach could gradually become less effective for long data streams, as the model may memorize the stored examples and overfit the memory buffer. Second, existing methods overlook the high uncertainty in the memory data distribution since there is a big gap between the memory data distribution and the distribution of all the previous data examples. To address these problems, for the first time, we propose a principled memory evolution framework to dynamically evolve the memory data distribution by making the memory buffer gradually harder to be memorized with distributionally robust optimization (DRO). We then derive a family of methods to evolve the memory buffer data in the continuous probability measure space with Wasserstein gradient flow (WGF). The proposed DRO is w.r.t the worst-case evolved memory data distribution, thus guarantees the model performance and learns significantly more robust features than existing memory-replay-based methods. Extensive experiments on existing benchmarks demonstrate the effectiveness of the proposed methods for alleviating forgetting. As a by-product of the proposed framework, our method is more robust to adversarial examples than existing task-free CL methods. Code is available on GitHub \\url{https://github.com/joey-wang123/DRO-Task-free}","url_abs":"https://arxiv.org/abs/2207.07256v2","url_pdf":"https://arxiv.org/pdf/2207.07256v2.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":"improving-task-free-continual-learning-by","repo_url":"https://github.com/joey-wang123/DRO-Task-free","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.07256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.07256"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/joey-wang123/DRO-Task-free","reach":null}],"summary":{"ran_draft_wrong":3,"ran_fixture":2},"by_repo_kind":{"official":{"samples":5,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"bb45173f2c1e0b85","entry":"SGLD_step","repo":"joey-wang123/DRO-Task-free","repo_kind":"official","path":"WGF.py","file_url":"https://github.com/joey-wang123/DRO-Task-free/blob/HEAD/WGF.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb45173f2c1e0b85"}},{"code_sha256_prefix":"b40fd105a84e61c1","entry":"SVGD_kernal","repo":"joey-wang123/dro-task-free","repo_kind":"official","path":"WGF.py","file_url":"https://github.com/joey-wang123/dro-task-free/blob/HEAD/WGF.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b40fd105a84e61c1"}},{"code_sha256_prefix":"9775a658736ec278","entry":"SVGD_step","repo":"joey-wang123/dro-task-free","repo_kind":"official","path":"WGF.py","file_url":"https://github.com/joey-wang123/dro-task-free/blob/HEAD/WGF.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9775a658736ec278"}},{"code_sha256_prefix":"4b54dcf0c81ce82d","entry":"WGF_retrieve_replay_update","repo":"joey-wang123/dro-task-free","repo_kind":"official","path":"WGF.py","file_url":"https://github.com/joey-wang123/dro-task-free/blob/HEAD/WGF.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b54dcf0c81ce82d"}},{"code_sha256_prefix":"4ba4ef2010aed900","entry":"WGF_retrieve_replay_update","repo":"joey-wang123/DRO-Task-free","repo_kind":"official","path":"WGF.py","file_url":"https://github.com/joey-wang123/DRO-Task-free/blob/HEAD/WGF.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ba4ef2010aed900"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}