📝 Publications

Yi Wen, Yue Liu, Derong Xu, Huishi Luo, Pengyue Jia, Yiqing Wu, Siwei Wang, Ke Liang, Maolin Wang^#, Yiqi Wang, Fuzhen Zhuang^#, Xiangyu Zhao^#. Code PDF

• We introduce a domain selection principle (SDSP), leveraging both the supervised signals and the unsupervised distance measure to select beneficial domains. Besides, SDSP can be integrated into existing MDR methods to improve their performance.

Yi Wen, Siwei Wang^#, Ke Liang, Weixuan Liang, Xinhang Wan, Xinwang Liu^#, Suyuan Liu, Jiyuan Liu, En Zhu. Code PDF

• In order to solve the Anchor-Unaligned Problem for Incomplete Data, a novel alignment module is proposed in this paper to capture the view-specific structure. With the guidance of structure information, the cross-view anchor correspondence mapping can be refined adequately.

Yi Wen^*, Suyuan Liu^*, Xinhang Wan, Siwei Wang, Ke Liang, Xinwang Liu^#, Xihong Yang, Pei Zhang. Code PDF

• We design an anchor graph learning framework termed Efficient Multi-View Graph Clustering with Local and Global Structure Preservation (EMVGC-LG). With the proven properties, the proposed anchor graph paradigm can not only capture the global structure between data but also well approximate the local structure.

Yi Wen, Siwei Wang, Qing Liao, Weixuan Liang, Ke Liang, Xinhang Wan, Xinwang Liu^#. Code PDF

• We propose a new paradigm for graph-based MVC termed Data-Unpaired Problem (DUP). Our solution to this problem is of great significance and can avoid the strong assumption of the alignment of cross-view data in data collection.