Related work

The foundational work on continual learning, 1988 to 2026: methods, theory, benchmarks, surveys, and the neuroscience of memory. Updated weekly; some carry our notes.

22 papers of 6,984Sort Recent · Most cited

2022 Preprint Clear all

2022
Federated Continual Learning with Differentially Private Data SharingGiulio Zizzo, Ambrish Rawat, N. Holohan, Seshu TirupathiPreprint
2022
Speeding-up Continual Learning through Information Gains in Novel ExperiencesPierrick Lorang, Shivam Goel, Patrik Zips … matthias. scheutzPreprint
2022
Deep Learning for Class-Incremental Learning: A surveyDa-Wei Zhou, Fu Lee Wang, Han-Jia Ye, De-chuan ZhanPreprint
2022
E FFECT OF MODEL AND PRETRAINING SCALE ON CATASTROPHIC FORGETTING IN NEURAL NETWORKSV. Ramasesh, Aitor Lewkowycz, Ethan DyerPreprint
2022
Continual Learning for Time-to-Event ModelingManisha Dubey, P. K. Srijith, M. DesarkarPreprint
2022
Continual Poisoning of Generative Models to Promote Catastrophic ForgettingSiteng Kang, Zhan Shi, Xinhua ZhangPreprint
2022
Can Sequential Bayesian Inference Solve Continual Learning?Samuel Kessler, Adam D. Cobb, S. Zohren, Stephen J. RobertsPreprint
2022
Deep knowledge transfer for generalization across tasks and domains under data scarcity: on intersections of anomaly detection, few-shot learning, continual learning, domain generalization and data-free learningA. FrikhaPreprint
2022
Populating Memory in Continual Learning with Consistency Aware SamplingJ. Hurtado, Alain Raymond-Sáez, Vladimir Araujo … D. BacciuPreprint
2022
Supplementary Material: Continual Learning with Lifelong Vision TransformerZhen Wang, Liu Liu, Yiqun Duan … Dacheng TaoPreprint
2022
Title: Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals Short title: A neural network model of human continual learningTimo Flesch, D. G. Nagy, Andrew M. Saxe, C. SummerfieldPreprint
2022
CL-LSG: Continual Learning via Learnable Sparse GrowthLi Yang, Sen Lin, Junshan Zhang, Deliang FanPreprint
2022
Class-Incremental Learning with Strong Pre-trained Models Supplemental MaterialTz-Ying Wu, Gurumurthy Swaminathan, Zhizhong Li … S. SoattoPreprint
2022
Continual Learning for Computer Vision. (Apprentissage continu pour la vision par ordinateur)Arthur DouillardPreprint
2022
Continual Learning for Scene Analysis in Open WorldRomaric Audigier, Hejer AmmarPreprint
2022
Do Pre-trained Models Benefit Equally in Continual Learning? Supplementary MaterialKuan-Ying Lee, Yuanyi Zhong, Yu-Xiong WangPreprint
2022
Efficient Meta Continual Learning on the EdgeYoung D. KwonPreprint
2022
Elastic Weight Consolidation for Reduction of Catastrophic Forgetting in GPT-2Rishi Bommasani, Drew A. Hudson, Ehsan Adeli … D. LuanPreprint
2022
Knowledge uncertainty and lifelong learning in neural systemsChristian HenningPreprint
2022
Supplementary material for ”FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning”Grégoire Petit, Adrian-Ştefan Popescu, Hugo Schindler … Bertrand DelezoidePreprint
2022
Supplementary Materials for ”SSFE-Net: Self-Supervised Feature Enhancement for Ultra-Fine-Grained Few-Shot Class Incremental Learning”Zicheng Pan, Xiaohan Yu, Miaohua Zhang, Yongsheng GaoPreprint
2022
Supplementary: CAM-GAN: Continual Adaptation Modules for Generative Adversarial NetworksSakshi Varshney, V. Verma, P. K. Srijith … Piyush RaiPreprint

About this index

We keep this list because we read the field and wanted one place to see it. It covers work on continual learning itself, in the core areas of machine learning, and leaves out papers that apply it inside another field, such as medical imaging or fault diagnosis. It lists only papers we have a reason to trust: published at a venue like NeurIPS, ICML, ICLR, CVPR or TPAMI, or led by someone who has published there, or cited a few hundred times. Preprints that later get accepted, and authors who later publish at those venues, are picked up by the weekly run. It is seeded from the community lists kept by ContinualAI and by Xialei Liu, then filled out from OpenAlex, and every week a script looks for new papers on OpenAlex and arXiv. A model reads each candidate and decides whether it belongs; a person reviews the additions before they go live. Authors and affiliations come from OpenAlex, so a recent preprint can lack its institutions for a week or two.

Missing something, or filed under the wrong venue? Write to hello@unify.ai with the arXiv id or DOI.