ICML

TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration

Cheng Xin, Fan Xu, Xin Ding, Jie Gao, Jiaxin Ding

机构 * School of Computer Science, Shanghai Jiao Tong University, Shanghai, China（上海交通大学计算机科学学院） ； Department of Computer Science, Rutgers University, Piscataway, NJ, USA（罗格斯大学计算机科学系） 纠错

Comments submitted to ICML 2025

Breaking Barriers: Combinatorial Algorithms for Non-monotone Submodular Maximization with Sublinear Adaptivity and $1/e$ Approximation

Yixin Chen, Wenjing Chen, Alan Kuhnle

Comments Accepted by ICML 2025

Learning Safe Strategies for Value Maximizing Buyers in Uniform Price Auctions

Negin Golrezaei, Sourav Sahoo

机构 * Sloan School of Management, Massachusetts Institute of Technology（麻省理工学院斯隆管理学院） ； Operations Research Center, Massachusetts Institute of Technology（麻省理工学院运筹学研究中心） 纠错

Comments 84 pages, 5 figures. Appeared at ICML 2025. Fixed typos

Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups

Weiqiu You, Helen Qu, Marco Gatti, Bhuvnesh Jain, Eric Wong

机构 * Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA, USA（计算机与信息科学系，宾夕法尼亚大学，费城，PA，美国） ； Department of Physics and Astronomy, University of Pennsylvania, Philadelphia, PA, USA（物理与天文学系，宾夕法尼亚大学，费城，PA，美国） 纠错

Comments ICML 2025