{"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/uncertainty-based-continual-learning-with","title":"Uncertainty-based Continual Learning with Adaptive Regularization","arxiv_id":"1905.11614","date":"2019-05-28","proceeding":"NeurIPS 2019 12","authors":["Hongjoon Ahn","Sungmin Cha","DongGyu Lee","Taesup Moon"],"abstract":"We introduce a new neural network-based continual learning algorithm, dubbed as Uncertainty-regularized Continual Learning (UCL), which builds on traditional Bayesian online learning framework with variational inference. We focus on two significant drawbacks of the recently proposed regularization-based methods: a) considerable additional memory cost for determining the per-weight regularization strengths and b) the absence of gracefully forgetting scheme, which can prevent performance degradation in learning new tasks. In this paper, we show UCL can solve these two problems by introducing a fresh interpretation on the Kullback-Leibler (KL) divergence term of the variational lower bound for Gaussian mean-field approximation. Based on the interpretation, we propose the notion of node-wise uncertainty, which drastically reduces the number of additional parameters for implementing per-weight regularization. Moreover, we devise two additional regularization terms that enforce stability by freezing important parameters for past tasks and allow plasticity by controlling the actively learning parameters for a new task. Through extensive experiments, we show UCL convincingly outperforms most of recent state-of-the-art baselines not only on popular supervised learning benchmarks, but also on challenging lifelong reinforcement learning tasks. The source code of our algorithm is available at https://github.com/csm9493/UCL.","url_abs":"https://arxiv.org/abs/1905.11614v3","url_pdf":"https://arxiv.org/pdf/1905.11614v3.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":"uncertainty-based-continual-learning-with","repo_url":"https://github.com/csm9493/UCL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"uncertainty-based-continual-learning-with","repo_url":"https://github.com/Minhchuyentoancbn/Continual-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/continual-learning-on-asc-19-tasks","task":"Continual Learning","dataset":"ASC (19 tasks)","model":"UCL","rank_in_archive_order":11,"of":15,"metrics":{"F1 - macro":"0.7599"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.11614","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11614"}},"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/csm9493/UCL","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Minhchuyentoancbn/Continual-Learning","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"e71c2a2bc2fc8909","entry":"compute_conv_output_size","repo":"csm9493/UCL","repo_kind":"official","path":"networks/conv_net_omniglot_ucl.py","file_url":"https://github.com/csm9493/UCL/blob/HEAD/networks/conv_net_omniglot_ucl.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e71c2a2bc2fc8909"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}