{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T18:37:43Z","timestamp":1769279863088,"version":"3.49.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["IIS-1910492"],"award-info":[{"award-number":["IIS-1910492"]}]},{"name":"NSF","award":["IIS-223953"],"award-info":[{"award-number":["IIS-223953"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tpami.2023.3317874","type":"journal-article","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T17:41:16Z","timestamp":1695318076000},"page":"14337-14352","source":"Crossref","is-referenced-by-count":5,"title":["Distributionally Robust Memory Evolution With Generalized Divergence for Continual Learning"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2780-9446","authenticated-orcid":false,"given":"Zhenyi","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Maryland, College Park, MD, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5659-3464","authenticated-orcid":false,"given":"Li","family":"Shen","sequence":"additional","affiliation":[{"name":"JD Explore Academy, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4323-642X","authenticated-orcid":false,"given":"Tiehang","family":"Duan","sequence":"additional","affiliation":[{"name":"Meta Inc, Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8072-6060","authenticated-orcid":false,"given":"Qiuling","family":"Suo","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, State University of New York at Buffalo, Buffalo, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8923-537X","authenticated-orcid":false,"given":"Le","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, State University of New York at Buffalo, Buffalo, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3865-8145","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent Data Platform, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5488-8514","authenticated-orcid":false,"given":"Mingchen","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, State University of New York at Buffalo, Buffalo, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16861"},{"key":"ref57","article-title":"Memory replay with data compression for continual learning","author":"wang","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref12","article-title":"CPR: Classifier-projection regularization for continual learning","author":"cha","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref56","first-page":"5742","article-title":"Variational inference with tail-adaptive f-divergence","author":"wang","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","article-title":"Continual learning with tiny episodic memories","author":"chaudhry","year":"2019"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00882"},{"key":"ref14","article-title":"Efficient lifelong learning with A-GEM","author":"chaudhry","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_36"},{"key":"ref53","article-title":"Three scenarios for continual learning","author":"van de ven","year":"2019"},{"key":"ref52","first-page":"2990","article-title":"Continual learning with deep generative replay","author":"shin","year":"2017","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref55","article-title":"Continual learning with hypernetworks","author":"von oswald","year":"2019"},{"key":"ref10","article-title":"New insights on reducing abrupt representation change in online continual learning","author":"caccia","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref54","first-page":"3637","article-title":"Matching networks for one shot learning","author":"vinyals","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref17","first-page":"2098","article-title":"SVGD as a kernelized wasserstein gradient flow of the chi-squared divergence","author":"chewi","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"1683","article-title":"Stochastic gradient Hamiltonian Monte Carlo","author":"chen","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref19","first-page":"3366","article-title":"A continual learning survey: Defying forgetting in classification tasks","volume":"44","author":"delange","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref18","first-page":"1952","article-title":"Online continual learning from imbalanced data","author":"chrysakis","year":"2020","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref51","first-page":"4555","article-title":"Overcoming catastrophic forgetting with hard attention to the task","author":"serr\u00e1","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","first-page":"4535","article-title":"Progress and compress: A scalable framework for continual learning","author":"schwarz","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref46","article-title":"Learning to learn without forgetting by maximizing transfer and minimizing interference","author":"riemer","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref45","first-page":"7645","article-title":"Continual unsupervised representation learning","author":"rao","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","article-title":"Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization","author":"sagawa","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref47","article-title":"Progressive neural networks","author":"rusu","year":"2016"},{"key":"ref42","article-title":"Contextual transformation networks for online continual learning","author":"pham","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref41","article-title":"Variational continual learning","author":"nguyen","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref44","article-title":"Distributionally robust optimization: A review","author":"rahimian","year":"2019"},{"key":"ref43","article-title":"Looking back on learned experiences for class\/task incremental learning","author":"pourkeshavarzi","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref49","article-title":"Gradient projection memory for continual learning","author":"saha","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref7","first-page":"31886","article-title":"On the effectiveness of Lipschitz-driven rehearsal in continual learning","author":"bonicelli","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","article-title":"Dark experience for general continual learning: A strong, simple baseline","author":"buzzega","year":"2020","journal-title":"Proc 34th Int Conf Neural Inf Process Syst"},{"key":"ref4","article-title":"Gradient flows: In metric spaces and in the space of probability measures","author":"ambrosio","year":"2008","journal-title":"Lectures in Mathematics"},{"key":"ref3","article-title":"Gradient based sample selection for online continual learning","author":"aljundi","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","article-title":"Quantifying distributional model risk via optimal transport","author":"blanchet","year":"2017"},{"key":"ref5","author":"bass","year":"2011","journal-title":"Stochastic Processes Cambridge Series in Statistical and Probabilistic Mathematics"},{"key":"ref40","article-title":"Calculus of variations","author":"miersemann","year":"2012"},{"key":"ref35","first-page":"3115","article-title":"Stein variational gradient descent as gradient flow","author":"liu","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","first-page":"4093","article-title":"Understanding MCMC dynamics as flows on the Wasserstein space","author":"liu","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","first-page":"6467","article-title":"Gradient episodic memory for continual learning","author":"lopez-paz","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","first-page":"2370","article-title":"Stein variational gradient descent: A general purpose Bayesian inference algorithm","author":"liu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","article-title":"A neural Dirichlet process mixture model for task-free continual learning","author":"lee","year":"2020","journal-title":"Proc 17th Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2019.0198"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s40687-019-0198-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01151"},{"key":"ref1","first-page":"11849","article-title":"Online continual learning with maximal interfered retrieval","author":"aljundi","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref39","article-title":"Towards deep learning models resistant to adversarial attacks","author":"madry","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref38","first-page":"2917","article-title":"A complete recipe for stochastic gradient MCMC","author":"ma","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref68","first-page":"12345","article-title":"Doro: Distributional and outlier robust optimization","author":"zhai","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00118"},{"key":"ref67","article-title":"Task agnostic continual learning using online variational bayes","author":"zeno","year":"2019"},{"key":"ref26","first-page":"29193","article-title":"Gradient-based editing of memory examples for online task-free continual learning","author":"jin","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","article-title":"Task agnostic continual learning via meta learning","author":"he","year":"2019"},{"key":"ref20","article-title":"Uncertainty-guided continual learning with Bayesian neural networks","author":"ebrahimi","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref64","article-title":"Class-weighted classification: Trade-offs and robust approaches","author":"xu","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref63","first-page":"2093","article-title":"Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problem","author":"wibisono","year":"2018","journal-title":"Proc Conf Learn Theory"},{"key":"ref22","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref66","first-page":"3987","article-title":"Continual learning through synaptic intelligence","author":"zenke","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref21","article-title":"PathNet: Evolution channels gradient descent in super neural networks","author":"fernando","year":"2017"},{"key":"ref65","article-title":"Lifelong learning with dynamically expandable networks","author":"yoon","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"kirkpatrick","year":"2017","journal-title":"Proc Nat Acad Sci USA"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1137\/S0036141096303359"},{"key":"ref29","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00782"},{"key":"ref62","first-page":"681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","author":"welling","year":"2011","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref61","first-page":"22985","article-title":"Improving task-free continual learning by distributionally robust memory evolution","author":"wang","year":"2022","journal-title":"Proc 39th Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/10308548\/10258417-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10308548\/10258417.pdf?arnumber=10258417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:55:05Z","timestamp":1701114905000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10258417\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":68,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3317874","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}