持续学习应超越增量分类
Continual Learning Should Move Beyond Incremental Classification
AI总结：
本文立场指出持续学习不应局限于增量分类，并通过多类非分类场景分析三大核心挑战，提出形式化时间动态、连续任务空间及生成式目标等建议。
摘要：
持续学习（CL）是机器学习的一个子领域，关注在动态环境中积累知识。迄今为止，CL研究主要集中于增量分类任务，即模型学习对新类别进行分类，同时保留对先前已学类别的知识。本文认为，维持这种关注会限制CL方法的理论发展和实际适用性。通过对具体示例的详细分析——包括多目标分类、具有受限输出空间的机器人学、连续任务领域中的学习以及更高层次的概念记忆——我们展示了当前CL方法在应用于标准分类之外时往往会失败。我们识别出三个基本挑战：（C1）学习问题中连续性的本质，（C2）选择合适的空间和度量来衡量相似性，以及（C3）分类之外学习目标的作用。针对每个挑战，我们提供了具体建议以推动该领域发展，包括通过分布过程将时间动态形式化、为连续任务空间开发有原则的方法，以及纳入密度估计和生成式目标。通过这些工作，本立场论文旨在拓宽CL研究的范围，同时加强其理论基础，使其更适用于现实世界问题。
英文摘要：
Continual learning (CL) is the sub-field of machine learning concerned with accumulating knowledge in dynamic environments. So far, CL research has mainly focused on incremental classification tasks, where models learn to classify new categories while retaining knowledge of previously learned ones. Here, we argue that maintaining such a focus limits both theoretical development and practical applicability of CL methods. Through a detailed analysis of concrete examples - including multi-target classification, robotics with constrained output spaces, learning in continuous task domains, and higher-level concept memorization - we demonstrate how current CL approaches often fail when applied beyond standard classification. We identify three fundamental challenges: (C1) the nature of continuity in learning problems, (C2) the choice of appropriate spaces and metrics for measuring similarity, and (C3) the role of learning objectives beyond classification. For each challenge, we provide specific recommendations to help move the field forward, including formalizing temporal dynamics through distribution processes, developing principled approaches for continuous task spaces, and incorporating density estimation and generative objectives. In so doing, this position paper aims to broaden the scope of CL research while strengthening its theoretical foundations, making it more applicable to real-world problems.
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。
