Amortized Predictability-aware Training Framework for Time Series Forecasting and Classification
面向时间序列预测与分类的摊销可预测性感知训练框架
机构 * Shanghai Key Laboratory of Data Science, College of Computer Science and Artificial Intelligence Fudan University（复旦大学计算机科学与人工智能学院上海数据科学关键实验室） ； Department of Electrical and Computer Engineering University of British Columbia (UBC)（英属哥伦比亚大学电气与计算机工程系）
AI总结 提出APTF框架，通过分层可预测性感知损失和摊销模型识别并惩罚低可预测性样本，提升时间序列预测与分类性能。
Comments This work is accepted by the proceedings of the ACM Web Conference 2026 (WWW 2026). The code is available at the link https://github.com/Meteor-Stars/APTF
