持续学习是否同等遗忘所有参数？
Does Continual Learning Equally Forget All Parameters?
AI总结：
本文通过分析持续学习中模块的训练动态，发现遗忘主要由少数任务特定模块引起，提出高效方法FPF及$k$-FPF，在大幅提升性能的同时显著降低计算开销。
摘要：
持续学习（CL）中的分布偏移（例如任务或领域偏移）通常会导致神经网络的灾难性遗忘。尽管可以通过重复重放缓冲数据来缓解此问题，但每步重放非常耗时。在本文中，我们通过研究模块在CL期间的训练动态，研究神经网络中哪些模块更容易遗忘。我们提出的指标表明，只有少数模块更具任务特定性，并在任务间敏感地变化，而其他模块可以作为公共知识跨任务共享。因此，我们将遗忘主要归因于前者，并发现在任何CL方法结束时仅在小缓冲区上微调它们可以带来显著的改进。由于微调的参数数量很少，这种“遗忘优先微调（FPF）”在计算上是高效的。我们进一步提出了一种更高效、更简单的方法，该方法完全移除了每步重放，并用在CL期间周期性触发的仅$k$次FPF来替代它们。令人惊讶的是，这种“$k$-FPF”的性能与FPF相当，并且优于SOTA CL方法，同时显著降低了它们的计算开销和成本。在类增量和域增量CL的几个基准上的实验中，FPF持续大幅改进了现有的CL方法，而$k$-FPF在不降低准确性的情况下进一步在效率上表现出色。我们还实证研究了缓冲区大小、每任务轮数和微调模块对我们方法的成本和准确性的影响。
英文摘要：
Distribution shift (e.g., task or domain shift) in continual learning (CL) usually results in catastrophic forgetting of neural networks. Although it can be alleviated by repeatedly replaying buffered data, the every-step replay is time-consuming. In this paper, we study which modules in neural networks are more prone to forgetting by investigating their training dynamics during CL. Our proposed metrics show that only a few modules are more task-specific and sensitively alter between tasks, while others can be shared across tasks as common knowledge. Hence, we attribute forgetting mainly to the former and find that finetuning them only on a small buffer at the end of any CL method can bring non-trivial improvement. Due to the small number of finetuned parameters, such ``Forgetting Prioritized Finetuning (FPF)'' is efficient in computation. We further propose a more efficient and simpler method that entirely removes the every-step replay and replaces them by only $k$-times of FPF periodically triggered during CL. Surprisingly, this ``$k$-FPF'' performs comparably to FPF and outperforms the SOTA CL methods but significantly reduces their computational overhead and cost. In experiments on several benchmarks of class- and domain-incremental CL, FPF consistently improves existing CL methods by a large margin, and $k$-FPF further excels in efficiency without degrading the accuracy. We also empirically studied the impact of buffer size, epochs per task, and finetuning modules on the cost and accuracy of our methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
