反Hessian正则化用于语音识别中的持续学习
Inverse-Hessian Regularization for Continual Learning in ASR
AI总结:
本文提出反Hessian正则化(IHR),一种用于语音识别持续学习的无记忆方法,通过在合并步骤中引入曲率信息,减少灾难性遗忘并提高适应性。
摘要:
持续学习(CL)在自动语音识别(ASR)中面临灾难性遗忘的挑战,即模型必须适应新领域而不损失先前学习条件的性能。已有多种CL方法被提出,最近权重平均法在微调后通过合并步骤进行平均,成为一种简单的无记忆策略。然而,这种方法具有启发性性质,忽略了任务的潜在损失景观,限制了适应性。本文提出反Hessian正则化(IHR),一种用于ASR持续学习的无记忆方法,将曲率信息融入合并步骤。在微调新任务后,通过先前任务的Kronecker因子逆Hessian近似调整适应,确保模型主要在对过去性能有害较小的方向上移动,同时保持方法轻量。我们在两个CL基准上评估IHR,显示其显著优于最先进基线,减少遗忘并提高适应性。消融研究和分析进一步证实其有效性。
英文摘要:
Catastrophic forgetting remains a major challenge for continual learning (CL) in automatic speech recognition (ASR), where models must adapt to new domains without losing performance on previously learned conditions. Several CL methods have been proposed for ASR, and, recently, weight averaging - where models are averaged in a merging step after fine-tuning - has proven effective as a simple memory-free strategy. However, it is heuristic in nature and ignores the underlying loss landscapes of the tasks, hindering adaptability. In this work, we propose Inverse Hessian Regularization (IHR), a memory-free approach for CL in ASR that incorporates curvature information into the merging step. After fine-tuning on a new task, the adaptation is adjusted through a Kronecker-factored inverse Hessian approximation of the previous task, ensuring that the model moves primarily in directions less harmful to past performance, while keeping the method lightweight. We evaluate IHR on two CL benchmarks and show that it significantly outperforms state-of-the-art baselines, reducing forgetting while improving adaptability. Ablation studies and analyses further confirm its effectiveness.
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。