AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE
AnchorMoE: 基于锚点路由的混合专家模型实现可解释时间序列分类
机构 * School of Automation, Guangdong University of Technology(广东工业大学自动化学院) ; School of Computer Science and Technology, Guangdong University of Technology(广东工业大学计算机科学与技术学院) ; College of Computer Science and Software Engineering, Shenzhen University(深圳大学计算机科学与软件工程学院) ; School of Informatics, Xiamen University(厦门大学信息学院) ; State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University(东北大学过程工业综合自动化国家重点实验室) ; Department of Computer Science, Hong Kong Baptist University(香港 Baptist 大学计算机科学系)
AI总结 提出AnchorMoE框架,利用混合专家架构对局部补丁进行多视角表示并路由至专门专家,通过加性分解实现前向可解释性,并引入几何正交约束和不确定性感知门控机制提升稀疏信号下的分解可靠性与噪声抑制。
Comments Accepted by KDD 2026