The paper “TRUST-FS: Tensorized Reliable Unsupervised Multi-View Feature Selection for Incomplete Data”, co-authored by Ph.D. student Minghui Lu of Southwestern University of Finance and Economics, Prof. Yanyong Huang of Southwestern University of Finance and Economics , Prof. Jinyuan Chang from our team, Postdoctoral Fellow Minbo Ma of Tsinghua University, Prof. Dongjie Wang of Northeast Normal University, as well as Prof. Xiuwen Yi, Associate Prof. Fengmao Lü, and Prof. Tianrui Li of Southwest Jiaotong University, has been officially accepted by the Main Track of ACM International Conference on Multimedia (ACM MM 2026), one of the top international conferences in the field of multimedia.
Abstract
Multi-view unsupervised feature selection (MUFS), which selects informative features from multi-view unlabeled data, has attracted increasing research interest in recent years. Although great efforts have been devoted to MUFS, several challenges remain: 1) existing methods for incomplete multi-view data are limited to handling missing views and are unable to address the more general scenario of missing variables, where some features have missing values in certain views; 2) most methods address incomplete data by first imputing missing values and then performing feature selection, treating these two processes independently and overlooking their interactions; 3) missing data can result in an inaccurate similarity graph, which reduces the performance of feature selection. To solve this dilemma, we propose a novel MUFS method for incomplete multi-view data with missing variables, termed Tensorized Reliable UnSupervised mulTi-view Feature Selection (TRUST-FS). TRUST-FS introduces a new adaptive-weighted CP decomposition that simultaneously performs feature selection, missing-variable imputation, and view weight learning within a unified tensor factorization framework. By utilizing Subjective Logic to acquire trustworthy cross-view similarity information, TRUST-FS facilitates learning a reliable similarity graph, which subsequently guides feature selection and imputation. Comprehensive experimental results demonstrate the effectiveness and superiority of our method over state-of-the-art methods.
Author Introduction
Li Yang is a Ph.D. student at Southwestern University of Finance and Economics, supervised by Prof. Yanyong Huang. She primarily engaged in research related to data mining and pattern recognition.
Yanyong Huang is a Professor and Doctoral Supervisor at the Joint Laboratory of Data Science and Business Intelligence, Southwestern University of Finance and Economics. He primarily engaged in research related to Data-centric AI, multimodal learning, and incremental learning.
Minbo Ma is a Postdoctoral Fellow at Tsinghua University. He primarily engaged in interdisciplinary research related to the application of artificial intelligence and spatiotemporal data mining techniques in renewable energy and urban computing.
Jinyuan Chang is the Executive Director of the Joint Laboratory of Data Science and Business Intelligence at Southwestern University of Finance and Economics. He is a Guanghua Chair Professor and a recipient of the National Science Fund for Distinguished Young Scholars of China. He primarily engaged in research related to complex data analysis.
Dongjie Wang is a Professor at Northeast Normal University. He primarily engages in research related to Data-centric AI, causal graph learning, and spatio-temporal data mining.
Xiuwen Yi is a Professor at Southwest Jiaotong University and a Beijing Nova Program scholar. He primarily engages in research related to urban computing and data mining.
Fengmao Lü is an Associate Professor and Doctoral Supervisor at Southwest Jiaotong University. He primarily engages in research related to multimodal learning, open-world learning, multimedia content analysis, and artificial intelligence security.
Tianrui Li is a Professor at Southwest Jiaotong University and the Dean of the Sichuan Institute of Industrial Software Technology. He primarily engages in research related to artificial intelligence, data mining and knowledge discovery, cloud computing and big data, granular computing, and rough sets.
