演化领域的迁移学习
Transfer Learning for Evolving Domains
- Feedzai
- University of Porto（波尔图大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出演化领域迁移学习（TrED）问题，将经典迁移学习设置统一为动态数据可用性轨迹，并论证其为一个适定且未解决的重要研究方向。
AI中文摘要：
迁移学习探索如何利用来自各种任务或领域（源）的知识，以提升在相关任务或领域（目标）中的预测性能。通常，迁移学习研究被划分为几个孤立的子领域（如领域泛化、领域自适应或多领域学习），每个子领域对目标数据的可用性做出不同的假设，即在训练时可获得多少数据以及多少标签。然而，在许多实际应用中，数据的可用性并非固定不变，而是随时间演化，因为实例和标签会逐渐从一个新领域中被收集。每个经典设置因此仅描述了部署系统必须完整穿越的轨迹的一个快照。我们将这一轨迹本身形式化为一个迁移学习问题，即演化领域的迁移学习（TrED），其由环境固定的数据可用性过程、方法可自由选择的学习协议以及评估标准来规定，该评估标准对整个模型轨迹而非单一模型进行评分。在这一形式体系内，经典设置被恢复为学习者可能经过的机制，而非TrED串联的独立问题。随后，我们审视迁移学习文献，以识别有望作为解决方案构建模块的机制，并发现大多数方法针对单一机制定制，即便是现有最强的候选者也尚未优化整个轨迹。我们认为TrED是一个适定且未解决的问题，是未来研究的一个重要方向。
英文摘要：
Transfer learning explores how to leverage knowledge from various tasks or domains (sources) to enhance predictive performance in related tasks or domains (targets). Typically, transfer learning research is segmented into several isolated sub-areas (such as domain generalisation, domain adaptation, or multi-domain learning), each making distinct assumptions about target data availability, namely how much data and how many labels are available at training time. However, in many real-world applications, data availability is not fixed but evolves over time, as instances and labels are progressively collected from a new domain. Each of the classical settings then describes only a snapshot of a trajectory that a deployed system must traverse in full. We formalise this trajectory as a transfer learning problem in its own right, Transfer Learning for Evolving Domains (TrED), specified by a data availability process fixed by the environment, a learning protocol that the method is free to choose, and an evaluation criterion that scores the whole trajectory of models rather than a single one. Within this formalism, the classical settings are recovered as regimes that a learner may pass through, rather than as separate problems that TrED concatenates. We then examine the transfer learning literature to identify mechanisms that are promising building blocks for a solution, and find that most methods are tailored to a single regime and that even the strongest existing candidates do not yet optimise the whole trajectory. We argue that TrED is a well-posed and unsolved problem, and an important direction for future research.
