通过分层二次巩固缓解任务顺序敏感性和遗忘
Mitigating Task-Order Sensitivity and Forgetting via Hierarchical Second-Order Consolidation
AI总结：
本文提出HTCL框架，通过分层二次巩固缓解任务顺序敏感性和遗忘，提升持续学习性能。
摘要：
我们引入了基于泰勒级数的持续学习框架（HTCL），该框架将快速的局部适应与保守的二次全局巩固相结合，以解决随机任务顺序引入的高方差问题。为了解决任务顺序效应，HTCL确定最佳的组内任务序列，并通过Hessian正则化的泰勒展开整合由此产生的局部更新，从而得到具有理论保证的巩固步骤。该方法自然扩展到L级层次，使多尺度知识整合以一种传统单层持续学习系统不支持的方式得以实现。在广泛的数据显示集和回放和正则化基线中，HTCL作为一种模型无关的巩固层，始终增强性能，产生7%到25%的平均准确率提升，同时在随机任务排列中将最终准确率的标准差降低高达68%。
英文摘要：
We introduce $\textbf{Hierarchical Taylor Series-based Continual Learning (HTCL)}$, a framework that couples fast local adaptation with conservative, second-order global consolidation to address the high variance introduced by random task ordering. To address task-order effects, HTCL identifies the best intra-group task sequence and integrates the resulting local updates through a Hessian-regularized Taylor expansion, yielding a consolidation step with theoretical guarantees. The approach naturally extends to an $L$-level hierarchy, enabling multiscale knowledge integration in a manner not supported by conventional single-level CL systems. Across a wide range of datasets and replay and regularization baselines, HTCL acts as a model-agnostic consolidation layer that consistently enhances performance, yielding mean accuracy gains of $7\%$ to $25\%$ while reducing the standard deviation of final accuracy by up to $68\%$ across random task permutations.
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。
