Class-Adaptive Sampling Policy for Efficient Continual Learning (2311.16485v1)
Abstract: Continual learning (CL) aims to acquire new knowledge while preserving information from previous experiences without forgetting. Though buffer-based methods (i.e., retaining samples from previous tasks) have achieved acceptable performance, determining how to allocate the buffer remains a critical challenge. Most recent research focuses on refining these methods but often fails to sufficiently consider the varying influence of samples on the learning process, and frequently overlooks the complexity of the classes/concepts being learned. Generally, these methods do not directly take into account the contribution of individual classes. However, our investigation indicates that more challenging classes necessitate preserving a larger number of samples compared to less challenging ones. To address this issue, we propose a novel method and policy named 'Class-Adaptive Sampling Policy' (CASP), which dynamically allocates storage space within the buffer. By utilizing concepts of class contribution and difficulty, CASP adaptively manages buffer space, allowing certain classes to occupy a larger portion of the buffer while reducing storage for others. This approach significantly improves the efficiency of knowledge retention and utilization. CASP provides a versatile solution to boost the performance and efficiency of CL. It meets the demand for dynamic buffer allocation, accommodating the varying contributions of different classes and their learning complexities over time.
- Online continual learning with maximal interfered retrieval. In Advances in Neural Information Processing Systems. Curran Associates, Inc., 2019a.
- Gradient based sample selection for online continual learning. Advances in neural information processing systems, 32, 2019b.
- Data excellence for ai: why should you care? Interactions, 29(2):66–69, 2022.
- Riemannian walk for incremental learning: Understanding forgetting and intransigence. In Proceedings of the European conference on computer vision (ECCV), pages 532–547, 2018.
- On tiny episodic memories in continual learning. arXiv preprint arXiv:1902.10486, 2019.
- A continual learning survey: Defying forgetting in classification tasks. IEEE transactions on pattern analysis and machine intelligence, 44(7):3366–3385, 2021.
- Podnet: Pooled outputs distillation for small-tasks incremental learning. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XX 16, pages 86–102. Springer, 2020.
- Not just selection, but exploration: Online class-incremental continual learning via dual view consistency. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7442–7451, 2022.
- Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
- Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261, 2019.
- Curiosity-driven class-incremental learning via adaptive sample selection. IEEE Transactions on Circuits and Systems for Video Technology, 32(12):8660–8673, 2022.
- Dense network expansion for class incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11858–11867, 2023.
- Gradient-based editing of memory examples for online task-free continual learning. Advances in Neural Information Processing Systems, 34:29193–29205, 2021.
- On the stability-plasticity dilemma of class-incremental learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 20196–20204, 2023.
- Achieving a better stability-plasticity trade-off via auxiliary networks in continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11930–11939, 2023.
- Overcoming catastrophic forgetting in neural networks. Proceedings of the national academy of sciences, 114(13):3521–3526, 2017.
- Learning multiple layers of features from tiny images. 2009.
- Retrospective adversarial replay for continual learning. Advances in Neural Information Processing Systems, 35:28530–28544, 2022.
- Pcr: Proxy-based contrastive replay for online class-incremental continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 24246–24255, 2023.
- Adaptive aggregation networks for class-incremental learning. In Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition, pages 2544–2553, 2021.
- Gradient episodic memory for continual learning. Advances in neural information processing systems, 30, 2017.
- Supervised contrastive replay: Revisiting the nearest class mean classifier in online class-incremental continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3589–3599, 2021.
- Packnet: Adding multiple tasks to a single network by iterative pruning. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 7765–7773, 2018.
- Dataperf: Benchmarks for data-centric ai development. arXiv preprint arXiv:2207.10062, 2022.
- A data-centric approach for training deep neural networks with less data. arXiv preprint arXiv:2110.03613, 2021.
- “everyone wants to do the model work, not the data work”: Data cascades in high-stakes ai. In proceedings of the 2021 CHI Conference on Human Factors in Computing Systems, pages 1–15, 2021.
- Online class-incremental continual learning with adversarial shapley value. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 9630–9638, 2021.
- Regularizing second-order influences for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 20166–20175, 2023.
- Dataset cartography: Mapping and diagnosing datasets with training dynamics. arXiv preprint arXiv:2009.10795, 2020.
- Gcr: Gradient coreset based replay buffer selection for continual learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 99–108, 2022.
- An empirical study of example forgetting during deep neural network learning. arXiv preprint arXiv:1812.05159, 2018.
- Laurens Van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(11), 2008.
- Matching networks for one shot learning. Advances in neural information processing systems, 29, 2016.
- Improving task-free continual learning by distributionally robust memory evolution. In International Conference on Machine Learning, pages 22985–22998. PMLR, 2022.
- Continual recognition with adaptive memory update. ACM Transactions on Multimedia Computing, Communications and Applications, 19(3s):1–15, 2023.
- Online coreset selection for rehearsal-based continual learning. arXiv preprint arXiv:2106.01085, 2021.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
