Continual Learning

2025

• Muppidi, A., Zhang, Z. and Yang, H., 2025. Fast trac: A parameter-free optimizer for lifelong reinforcement learning. Advances in Neural Information Processing Systems, 37, pp.51169-51195.
• Feng, T., Li, W., Zhu, D., Yuan, H., Zheng, W., Zhang, D. and Tang, J., 2025. ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think. arXiv preprint arXiv:2501.01045.
• Yichen Wu, Hongming Piao, Long-Kai Huang, Renzhen Wang, Wanhua Li, Hanspeter Pfister, Deyu Meng, Kede Ma, and Ying Wei. Sd-lora: Scalable decoupled low-rank adaptation for class incremental learning. ICLR, 2025.[code]
• Liao, H., He, S., Hao, Y., Zhao, J. and Liu, K., 2025. DATA: Decomposed Attention-based Task Adaptation for Rehearsal-Free Continual Learning. arXiv preprint arXiv:2502.11482.[code]
• He, J., Duan, Z. and Zhu, F., 2025. CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental Learning. In Proceedings of the Computer Vision and Pattern Recognition Conference (pp. 30534-30544).[code]
• Wu, F., Cheng, L., Tang, S., Zhu, X., Fang, C., Zhang, D. and Wang, M., 2025. Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning. arXiv preprint arXiv:2502.07560.[code]
• Cheng, Q., Wan, Y., Wu, L., Hou, C. and Zhang, L., 2025. Continuous Subspace Optimization for Continual Learning. arXiv preprint arXiv:2505.11816.
• He, R., Fang, D., Xu, Y., Cui, Y., Li, M., Chen, C., Zeng, Z. and Zhuang, H., 2025. Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning. arXiv preprint arXiv:2503.05423.
• Li, L., Hu, T., Zhou, D.W., Ye, H.J. and Zhan, D.C., 2025. BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning. arXiv preprint arXiv:2511.11421.
• He, L., Cheng, D., Wang, H. and Wang, N., 2025. Harnessing Textual Semantic Priors for Knowledge Transfer and Refinement in CLIP-Driven Continual Learning. arXiv preprint arXiv:2508.01579.

2024

• Muppidi, A., Zhang, Z. and Yang, H., 2024. Pick up the PACE: A Parameter-Free Optimizer for Lifelong Reinforcement Learning . arXiv preprint arXiv:2405.16642. [website + python]
• Julian, J., Koh, Y.S. and Bifet, A., 2024, August. Sketch-Based Replay Projection for Continual Learning. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 1325-1335). [python]
• Wang, L., Xie, J., Zhang, X., Huang, M., Su, H. and Zhu, J., 2024. Hierarchical decomposition of prompt-based continual learning: Rethinking obscured sub-optimality. Advances in Neural Information Processing Systems, 36. [python]
• Hartvigsen, T., Sankaranarayanan, S., Palangi, H., Kim, Y. and Ghassemi, M., 2024. Aging with grace: Lifelong model editing with discrete key-value adaptors. Advances in Neural Information Processing Systems, 36.
• Elsayed, M. and Mahmood, A.R., 2024. Addressing loss of plasticity and catastrophic forgetting in continual learning. In International Conference on Learning Representations.
  • [Python]
• Wang, Zhenyi, Enneng Yang, Li Shen, and Heng Huang. A comprehensive survey of forgetting in deep learning beyond continual learning. [github] IEEE Transactions on Pattern Analysis and Machine Intelligence (2024).
• Bellitto, G., Proietto Salanitri, F., Pennisi, M., Boschini, M., Bonicelli, L., Porrello, A., Calderara, S., Palazzo, S. and Spampinato, C., 2024. Saliency-driven experience replay for continual learning. Advances in Neural Information Processing Systems, 37, pp.103356-103383.[code]
• Zhuang, H., Chen, Y., Fang, D., He, R., Tong, K., Wei, H., Zeng, Z. and Chen, C., 2024. GACL: Exemplar-free generalized analytic continual learning. Advances in Neural Information Processing Systems, 37, pp.83024-83047.[code]
• Zhou, D.W., Cai, Z.W., Ye, H.J., Zhan, D.C. and Liu, Z., 2025. Revisiting class-incremental learning with pre-trained models: Generalizability and adaptivity are all you need. International Journal of Computer Vision, 133(3), pp.1012-1032.[code]
• Liang, Y.S. and Li, W.J., 2024. Inflora: Interference-free low-rank adaptation for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 23638-23647).[code]
• Li, J., Lai, Y., Wang, R., Shui, C., Sahoo, S., Ling, C.X., Yang, S., Wang, B., Gagné, C. and Zhou, F., 2024. Hessian aware low-rank perturbation for order-robust continual learning. IEEE Transactions on Knowledge and Data Engineering.[code]
• Li, Q., Peng, Y. and Zhou, J., 2024. Fcs: Feature calibration and separation for non-exemplar class incremental learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 28495-28504).
• Xu, K., Zou, X., Peng, Y. and Zhou, J., 2024. Distribution-aware knowledge prototyping for non-exemplar lifelong person re-identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16604-16613).
• Zhang, H., Lei, Y., Gui, L., Yang, M., He, Y., Wang, H. and Xu, R., 2024, May. Cppo: Continual learning for reinforcement learning with human feedback. In The Twelfth International Conference on Learning Representations.

2023

• Abbas, Z., Zhao, R., Modayil, J., White, A. and Machado, M.C., 2023, November. Loss of plasticity in continual deep reinforcement learning. In Conference on Lifelong Learning Agents (pp. 620-636). PMLR. [python]
• Irie, K., Csordás, R. and Schmidhuber, J., 2023. Automating Continual Learning.
• Mok, J., Do, J., Lee, S., Taghavi, T., Yu, S. and Yoon, S., 2023, July. Large-scale lifelong learning of in-context instructions and how to tackle it. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 12573-12589). [website]
• Lu, P., Caprio, M., Eaton, E. and Lee, I., 2023. IBCL: Zero-shot Model Generation for Task Trade-offs in Continual Learning. arXiv preprint arXiv:2305.14782. [python]
• Anand, N. and Precup, D., 2024. Prediction and control in continual reinforcement learning. Advances in Neural Information Processing Systems, 36.
• Abbas, Z., Zhao, R., Modayil, J., White, A. and Machado, M.C., 2023, November. Loss of plasticity in continual deep reinforcement learning. In Conference on lifelong learning agents (pp. 620-636). PMLR.
• Lee, H., Cho, H., Kim, H., Gwak, D., Kim, J., Choo, J., Yun, S.Y. and Yun, C., 2023. Plastic: Improving input and label plasticity for sample efficient reinforcement learning. Advances in Neural Information Processing Systems,[python] 36, pp.62270-62295.
• Lyle, C., Zheng, Z., Nikishin, E., Pires, B.A., Pascanu, R. and Dabney, W., 2023, July. Understanding plasticity in neural networks. In International Conference on Machine Learning (pp. 23190-23211). PMLR.
• Nikishin, E., Oh, J., Ostrovski, G., Lyle, C., Pascanu, R., Dabney, W. and Barreto, A., 2023. Deep reinforcement learning with plasticity injection. Advances in Neural Information Processing Systems, 36, pp.37142-37159.
• Cha, H., Lee, J. and Shin, J., 2021. Co2l: Contrastive continual learning. In Proceedings of the IEEE/CVF International conference on computer vision (pp. 9516-9525).
• Sun, Z., Mu, Y. and Hua, G., 2023. Regularizing second-order influences for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 20166-20175).[code]
• Liang, Y.S. and Li, W.J., 2023. Adaptive plasticity improvement for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7816-7825).
• Shi, W. and Ye, M., 2023. Prototype reminiscence and augmented asymmetric knowledge aggregation for non-exemplar class-incremental learning. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 1772-1781).

2022

• Savage, N., 2022. Learning over a lifetime. Nature.
• Zhang, Y., Pfahringer, B., Frank, E., Bifet, A., Lim, N.J.S. and Jia, Y., 2022, November. Repeated augmented rehearsal: a simple but strong baseline for online continual learning. In Proceedings of the 36th International Conference on Neural Information Processing Systems (pp. 14771-14783).[python]
• Gaya, J.B., Doan, T., Caccia, L., Soulier, L., Denoyer, L. and Raileanu, R., 2022. Building a subspace of policies for scalable continual learning. arXiv preprint arXiv:2211.10445.
• Elsayed, M. and Mahmood, A.R., 2022. Hesscale: Scalable computation of hessian diagonals. arXiv preprint arXiv:2210.11639.
• Wang, Z., Zhang, Z., Lee, C.Y., Zhang, H., Sun, R., Ren, X., Su, G., Perot, V., Dy, J. and Pfister, T., 2022. Learning to prompt for continual learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 139-149).

2021

• Dohare, S., Sutton, R.S. and Mahmood, A.R., 2021. Continual backprop: Stochastic gradient descent with persistent randomness. arXiv preprint arXiv:2108.06325. [python]
• Gaya, J.B., Soulier, L. and Denoyer, L., 2021. Learning a subspace of policies for online adaptation in reinforcement learning. arXiv preprint arXiv:2110.05169.
• Ebrahimi, S., Petryk, S., Gokul, A., Gan, W., Gonzalez, J.E., Rohrbach, M. and Darrell, T., 2021. Remembering for the right reasons: Explanations reduce catastrophic forgetting. Applied AI letters, 2(4), p.e44.[code]
• Caccia, L., Aljundi, R., Asadi, N., Tuytelaars, T., Pineau, J. and Belilovsky, E., New Insights on Reducing Abrupt Representation Change in Online Continual Learning. In International Conference on Learning Representations.[code]
• De Lange, M., Aljundi, R., Masana, M., Parisot, S., Jia, X., Leonardis, A., Slabaugh, G. and Tuytelaars, T., 2021. [A continual learning survey: Defying forgetting in classification tasks]. IEEE transactions on pattern analysis and machine intelligence, 44(7), pp.3366-3385.
• Zhu, F., Zhang, X.Y., Wang, C., Yin, F. and Liu, C.L., 2021. Prototype augmentation and self-supervision for incremental learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 5871-5880).

2020

• Gupta, G., Yadav, K. and Paull, L., 2020. Look-ahead meta learning for continual learning. Advances in Neural Information Processing Systems, 33, pp.11588-11598.[python]
• Ash, J. and Adams, R.P., 2020. On warm-starting neural network training. Advances in neural information processing systems, 33, pp.3884-3894.
• Harrison, J., Sharma, A., Finn, C. and Pavone, M., 2020. Continuous meta-learning without tasks. Advances in neural information processing systems, 33, pp.17571-17581.[code]
• Buzzega, P., Boschini, M., Porrello, A., Abati, D. and Calderara, S., 2020. Dark experience for general continual learning: a strong, simple baseline. Advances in neural information processing systems, 33, pp.15920-15930.[code]
• Yu, L., Twardowski, B., Liu, X., Herranz, L., Wang, K., Cheng, Y., Jui, S. and Weijer, J.V.D., 2020. Semantic drift compensation for class-incremental learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 6982-6991).

2019

• Cutkosky, A., 2019, June. Combining online learning guarantees. In Conference on Learning Theory (pp. 895-913). PMLR.
• Aljundi, R., Lin, M., Goujaud, B. and Bengio, Y., 2019. Gradient based sample selection for online continual learning. Advances in neural information processing systems, 32.[code]

2018

• Cutkosky, A. and Orabona, F., 2018, July. Black-box reductions for parameter-free online learning in banach spaces. In Conference On Learning Theory (pp. 1493-1529). PMLR.

1950s

• SELFRIDGE, O., 1958. Pandemonium - A paradigm for learning. In Symposium on the Mechanization of Thought Processes. National Physical Laboratory, UK.