新方法让模型更好适应任务逐步变化的场景，还给出可计算的性能保证。
Supervised Learning with Evolving Tasks and Performance Guarantees
- 设计通用框架，自动适配任务顺序变化的多种学习场景
- 证明了有效样本量随任务演进而提升，且性能有可靠保障
- 适合持续学习、多任务学习等动态任务场景，理论实用兼备
多个监督学习场景由一系列分类任务组成。例如，多任务学习和持续学习旨在学习一个固定或随时间增长的任务序列。现有技术针对特定场景定制，难以泛化；且大多忽略任务顺序的重要性。然而，任务序列中连续任务常具有更高相似性，即任务在演化。本文提出一种适用于多种监督学习场景的方法，能自适应任务演化特性。与现有方法不同，本工作提供可计算的紧性能界，并解析刻画有效样本量的增长机制。在基准数据集上的实验表明，该方法在多种场景下均实现性能提升，且所给性能保证可靠可信。
原文摘要 · Abstract (English)
Multiple supervised learning scenarios are composed by a sequence of classification tasks. For instance, multi-task learning and continual learning aim to learn a sequence of tasks that is either fixed or grows over time. Existing techniques for learning tasks that are in a sequence are tailored to specific scenarios, lacking adaptability to others. In addition, most of existing techniques consider situations in which the order of the tasks in the sequence is not relevant. However, it is common that tasks in a sequence are evolving in the sense that consecutive tasks often have a higher similarity. This paper presents a learning methodology that is applicable to multiple supervised learning scenarios and adapts to evolving tasks. Differently from existing techniques, we provide computable tight performance guarantees and analytically characterize the increase in the effective sample size. Experiments on benchmark datasets show the performance improvement of the proposed methodology in multiple scenarios and the reliability of the presented performance guarantees.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。