arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.19245cs.LG
收藏

遗忘、无知还是短视: revisiting Online Continual Learning中的关键挑战

Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning

College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics(南京航空航天大学计算机科学与技术学院);School of Computer Science and Technology, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院)

Xinrui Wang, Chuanxing Geng, Wenhai Wan, Shao-yuan Li, Songcan Chen

AI总结:

本文重新审视在线持续学习中的关键挑战,指出除灾难性遗忘外还存在模型无知和短视问题,并提出NsCE框架以最小时间成本实现有效全局判别特征学习。

摘要:

在线持续学习要求模型从不断、无尽的数据流中学习。尽管该领域已付出巨大努力,但大多数研究都集中在缓解灾难性遗忘问题以获得更好的分类能力,代价是训练工作量大幅增加。它们忽略了在现实场景中(例如高速数据流环境),数据不会暂停以适应缓慢的模型。本文强调,模型吞吐量——定义为模型在单位时间内可处理的最大训练样本数——同样重要。它直接限制了模型可利用的数据量,并为当前方法带来了极具挑战性的困境。基于这一理解,我们从经验和理论角度重新审视OCL中的关键挑战,强调了除已充分记录的灾难性遗忘之外的两个关键问题:模型无知:OCL的单遍特性挑战模型在受限训练时间和存储容量内学习有效特征,导致有效学习与模型吞吐量之间的权衡;模型短视:OCL在当前任务上的局部学习特性导致模型采用过于简化的任务特定特征和过度稀疏的分类器,造成当前任务最优解与全局目标之间的差距。为解决这些问题,我们提出Non-sparse Classifier Evolution框架(NsCE),以最小时间成本促进有效的全局判别特征学习。NsCE在预训练模型帮助下整合非稀疏最大分离正则化和定向经验回放技术,实现新全局判别特征的快速获取。

英文摘要:

Online continual learning requires the models to learn from constant, endless streams of data. While significant efforts have been made in this field, most were focused on mitigating the catastrophic forgetting issue to achieve better classification ability, at the cost of a much heavier training workload. They overlooked that in real-world scenarios, e.g., in high-speed data stream environments, data do not pause to accommodate slow models. In this paper, we emphasize that model throughput -- defined as the maximum number of training samples that a model can process within a unit of time -- is equally important. It directly limits how much data a model can utilize and presents a challenging dilemma for current methods. With this understanding, we revisit key challenges in OCL from both empirical and theoretical perspectives, highlighting two critical issues beyond the well-documented catastrophic forgetting: Model's ignorance: the single-pass nature of OCL challenges models to learn effective features within constrained training time and storage capacity, leading to a trade-off between effective learning and model throughput; Model's myopia: the local learning nature of OCL on the current task leads the model to adopt overly simplified, task-specific features and excessively sparse classifier, resulting in the gap between the optimal solution for the current task and the global objective. To tackle these issues, we propose the Non-sparse Classifier Evolution framework (NsCE) to facilitate effective global discriminative feature learning with minimal time cost. NsCE integrates non-sparse maximum separation regularization and targeted experience replay techniques with the help of pre-trained models, enabling rapid acquisition of new globally discriminative features.

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。

↑