Scholarlink

<p>Continual learning (CL) is characterized by learning sequentially arriving tasks and behaving as if they were observed simultaneously. In order to prevent catastrophic forgetting of old tasks when learning new tasks, representative CL methods usually employ additional loss terms to balance their contributions (e.g., regularization and replay), modulated by deterministic hyperparameters. However, this strategy struggles to accommodate real-time changes in data distributions and also lacks robustness to subsequent unseen tasks, especially in online scenarios where CL is performed with a one-pass data stream. Inspired by adaptive weighting in multitask learning, we propose an innovative approach named learning uncertain hyperparameters (LUNCH) for adaptive balancing of task contributions in CL. Specifically, we formulate each CL-relevant hyperparameter as a function of optimizable uncertainty under the homoscedastic assumption and ensure its training stability through the exponential moving average of network parameters. We further devise an evaluation protocol that moderately adjusts the hyperparameter values and reports their impact on performance, so as to analyze the sensitivity of these sub-optimal values in realistic applications. We perform extensive experiments to demonstrate the effectiveness and robustness of our approach, which significantly improves online CL in a plug-in manner (e.g., up to 11.26% and 5.64% on Split CIFAR-100 and Split Mini-ImageNet, respectively) as well as offline CL. Our code is included in Supplementary Materials for examination and will be released upon acceptance.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

LUNCH: adaptive balancing of continual learning via hyperparameter uncertainty

  • 期刊论文

  • 发表日期：

    2026年3月9日

查看全文
  • Qingyi Pan,
  • Liyuan Wang,
  • Jingyi Zhang,
  • Jun Zhu

摘要

Continual learning (CL) is characterized by learning sequentially arriving tasks and behaving as if they were observed simultaneously. In order to prevent catastrophic forgetting of old tasks when learning new tasks, representative CL methods usually employ additional loss terms to balance their contributions (e.g., regularization and replay), modulated by deterministic hyperparameters. However, this strategy struggles to accommodate real-time changes in data distributions and also lacks robustness to subsequent unseen tasks, especially in online scenarios where CL is performed with a one-pass data stream. Inspired by adaptive weighting in multitask learning, we propose an innovative approach named learning uncertain hyperparameters (LUNCH) for adaptive balancing of task contributions in CL. Specifically, we formulate each CL-relevant hyperparameter as a function of optimizable uncertainty under the homoscedastic assumption and ensure its training stability through the exponential moving average of network parameters. We further devise an evaluation protocol that moderately adjusts the hyperparameter values and reports their impact on performance, so as to analyze the sensitivity of these sub-optimal values in realistic applications. We perform extensive experiments to demonstrate the effectiveness and robustness of our approach, which significantly improves online CL in a plug-in manner (e.g., up to 11.26% and 5.64% on Split CIFAR-100 and Split Mini-ImageNet, respectively) as well as offline CL. Our code is included in Supplementary Materials for examination and will be released upon acceptance.