提出CURE方法，动态管理表格数据流的上下文以提升预测性能
Bounded Context Management for Tabular Foundation Models on Stream Learning
- 基于不确定性与冗余度设计上下文增删策略
- 在7个数据流上相对传统方法提升27.0%
- 适用于多种基础模型，适合流式学习场景
表格数据流学习需在分布变化下对连续到达的样本进行预测。标准方法通过更新模型状态适应变化，而表格基础模型（TFMs）则依赖有标签上下文进行上下文内推理，使其天然适配流学习。这将挑战从模型更新转为上下文管理。本文提出未来信息视角，提炼出三项实用要求：保留近期样本、保留不确定样本、移除冗余样本。据此提出CURE（基于不确定性准入与冗余感知淘汰的上下文管理策略），采用熵门控准入和冗余感知淘汰机制。在七个数据流上，CURE相较经典流学习方法相对提升达27.0%，对多种TFM骨干网络均保持鲁棒性，并在各类策略中排名第一。代码与数据集见https://github.com/morcellinus/CURE-ICML-FMSD。
原文摘要 · Abstract (English)
Tabular stream learning requires predictions on sequentially arriving examples under distribution shift. While standard methods adapt by updating model states, tabular foundation models (TFMs) make predictions conditioned on a labeled context in an in-context manner, making them a natural alternative for stream learning. This shifts the challenge from how to update the model to how to manage the context. We propose a future information view that yields three practical requirements for context management: preserve recent examples, retain uncertain examples, and remove redundant examples. We instantiate these requirements as CURE (Context management via Uncertainty-aware admission and Redundancy aware Eviction), a context-managing policy with entropy-gated admission and redundancy-aware eviction. Across seven streams, CURE shows up to 27.0% relative improvement over classical stream learners, remains robust across multiple TFM backbones, and ranks first among other policy variants. Code and datasets are available at https://github.com/morcellinus/CURE-ICML-FMSD.
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。