基于权重插值的持续学习
Continual Learning with Weight Interpolation
AI总结：
本文提出在持续学习各新任务后插值融合新旧模型权重的权重整合方法，以缓解灾难性遗忘、调节稳定性—可塑性权衡，并显著增强现有经验回放算法。
摘要：
持续学习对现代机器学习系统构成了一项根本性挑战，它要求模型在适应新任务的同时保留来自先前任务的知识。应对这一挑战需要开发能够从数据流中学习并随时间积累知识的高效算法。本文提出了一种利用权重整合方法的持续学习新途径。我们的方法是一种简单而强大的技术，通过在每个新任务之后在旧模型权重与新模型权重之间进行插值，增强模型对灾难性遗忘的鲁棒性，从而有效合并两个模型，以促进对新概念到来后出现的局部极小值的探索。此外，我们证明该方法可以补充现有基于演练的回放方法，提高其准确率并进一步缓解遗忘现象。同时，我们的方法为控制稳定性—可塑性权衡提供了一种直观机制。实验结果表明，所提出的权重整合方法为最先进的经验回放算法带来了显著的性能提升。我们的算法可从 https://github.com/jedrzejkozal/weight-interpolation-cl 下载。
英文摘要：
Continual learning poses a fundamental challenge for modern machine learning systems, requiring models to adapt to new tasks while retaining knowledge from previous ones. Addressing this challenge necessitates the development of efficient algorithms capable of learning from data streams and accumulating knowledge over time. This paper proposes a novel approach to continual learning utilizing the weight consolidation method. Our method, a simple yet powerful technique, enhances robustness against catastrophic forgetting by interpolating between old and new model weights after each novel task, effectively merging two models to facilitate exploration of local minima emerging after arrival of new concepts. Moreover, we demonstrate that our approach can complement existing rehearsal-based replay approaches, improving their accuracy and further mitigating the forgetting phenomenon. Additionally, our method provides an intuitive mechanism for controlling the stability-plasticity trade-off. Experimental results showcase the significant performance enhancement to state-of-the-art experience replay algorithms the proposed weight consolidation approach offers. Our algorithm can be downloaded from https://github.com/jedrzejkozal/weight-interpolation-cl.
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。
