根据层的不确定性动态调节学习，缓解持续学习中的遗忘问题。
Dynamic Feedback Engines: Layer-Wise Control for Self-Regulating Continual Learning
- 按各层分类熵动态调节学习强度，高熵层降熵防欠拟合，低熵层升熵防过拟合。
- 在多个数据集上显著优于现有基线，最高提升达12.3%准确率。
- 适用于各类持续学习方法，尤其适合需要稳定与灵活平衡的场景。
持续学习旨在学习新任务的同时保持对旧任务的性能，但多数方法面临灾难性遗忘问题。现有方法通常对所有层采用统一处理，常在稳定性与可塑性间权衡。然而，不同层在分类任务时自然表现出不同的不确定性（熵）。高熵层易因无法捕捉特定模式而欠拟合，低熵层则因过度自信和专一化而过拟合。为此，我们提出一种基于熵感知的持续学习方法，通过动态反馈机制根据每层熵值进行调控：降低高熵层的熵以缓解欠拟合，提高过度自信层的熵以减轻过拟合。这种自适应调节促使模型收敛至更宽的局部极小值，已被证明可提升泛化能力。该方法具有通用性，可无缝集成于基于回放或正则化的各类方法中。在多个数据集上的实验表明，其性能显著超越当前最优持续学习基线。
原文摘要 · Abstract (English)
Continual learning aims to acquire new tasks while preserving performance on previously learned ones, but most methods struggle with catastrophic forgetting. Existing approaches typically treat all layers uniformly, often trading stability for plasticity or vice versa. However, different layers naturally exhibit varying levels of uncertainty (entropy) when classifying tasks. High-entropy layers tend to underfit by failing to capture task-specific patterns, while low-entropy layers risk overfitting by becoming overly confident and specialized. To address this imbalance, we propose an entropy-aware continual learning method that employs a dynamic feedback mechanism to regulate each layer based on its entropy. Specifically, our approach reduces entropy in high-entropy layers to mitigate underfitting and increases entropy in overly confident layers to alleviate overfitting. This adaptive regulation encourages the model to converge to wider local minima, which have been shown to improve generalization. Our method is general and can be seamlessly integrated with both replay- and regularization-based approaches. Experiments on various datasets demonstrate substantial performance gains over state-of-the-art continual learning baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。