🧐 About Me

Xinhang Wan (万欣航) is a Ph.D student at degree College of Computer Science and Technology, National University of Defence Technology (NUDT). He is supervised by Prof. Xinwang Liu and Prof. En Zhu in Pattern Recognition & Machine Intelligence Lab (PRMI).

He is currently a visiting student in the PLUS Lab at ShanghaiTech under the guidance of Xuming He.

I anticipate completing my PhD by late 2025. Please feel free to contact me early.

Research Interests: Affordance learning, Multi-view Learning, Continual Learning, Active Learning, Semi-supervised Classification, Clustering.

Contact: wanxinhang@nudt.edu.cn

🔥 News

(Papers as first author are bolded.)

• 2024.06:   Will talk at AI TIME.
• 2024.05:   One paper has been accepted by IEEE-TKDE (CCF A).
• 2024.05:   Two papers have been accepted by ICML 2024 (CCF A).
• 2024.03:   One paper has been accepted by IEEE-TIP (CCF A, SCI 1区).
• 2024.03:   One paper has been accepted by IEEE-TNNLS (CCF B, SCI 1区).
• 2023.07:   Two papers have been accepted by ACM MM 2023 (CCF A).
• 2023.06:   One paper has been accepted by IEEE-TNNLS (CCF B, SCI 1区).
• 2022.12:   One paper has been accepted by AAAI 2023 (CCF A).
• 2022.06:   One paper has been accepted by ACM MM 2022 (CCF A).

📝 Publications

(^* indicates equal contribution; ^# indicates corresponding authorship.)

ICML 2024

Decouple then Classify: A Dynamic Multi-view Labeling Strategy with Shared and Specific Information

Xinhang Wan, Jiyuan Liu, Xinwang Liu^#, Yi Wen, Hao Yu, Siwei Wang, Shengju Yu, Tianjiao Wan, Jun Wang, En Zhu^#. Code PDF

• We propose an efficient algorithm to tackle the sample labeling task in semi-supervised multi-view learning. The samples of low classification confidence are labeled as high priorities.

IEEE-TIP

Fast Continual Multi-View Clustering with Incomplete Views

Xinhang Wan, Bin Xiao, Xinwang Liu^#, Jiyuan Liu, Weixuan Liang, En Zhu^#. Code PDF

• We study a new paradigm for large-scale multi-view clustering called the incomplete continual data problem (ICDP) and propose FCMVC-IV to tackle the problem.

IEEE-TNNLS

One-step Multi-view Clustering with Diverse Representation

Xinhang Wan, Jiyuan Liu, Xinbiao Gan, Xinwang Liu^#, Siwei Wang, Yi Wen, Tianjiao Wan, En Zhu^#. Code PDF

• By directly calculating the distance among samples with diverse representation, we incorporate matrix factorization and k-means into a unified framework with linear complexity. They negotiate with each other and boost the clustering performance.

AAAI 2023 (oral)

Auto-weighted Multi-view Clustering for Large-scale Data

Xinhang Wan, Xinwang Liu^#, Jiyuan Liu, Siwei Wang, Yi Wen, Weixuan Liang, En Zhu, Zhe Liu, Lu Zhou. Code PDF

• We remove the non-negative constraint of non-negative matrix factorization and obtain coefficient matrices with view-specific base matrices of different dimensions, then integrate them into a consensus one in a parameter-free way.

ACM MM 2022

Continual Multi-view Clustering

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

• We propose CMVC and it is the first attempt to handle real-time issues in late fusion multi-view clustering literature and will provide an inspiration for future research.

IEEE-TNNLS(major revision)

Contrastive Continual Multi-view Clustering with Filtered Structural Fusion

Xinhang Wan, et al. PDF

• We study a new paradigm on continual multi-view clustering, termed catastrophic forgetting problem (CFP). A clustering then sample strategy is deployed to extract and update the filtered structure information of prior views, then the attained information will guide the clustering when a new view arrives.

• Multiple Kernel Clustering with Adaptive Multi-scale Partition Selection, Jun Wang, Zhenglai Li, Chang Tang^#, Suyuan Liu, Xinhang Wan, Xinwang Liu^#, IEEE-TKDE. Code PDF
• Towards Resource-friendly, Extensible and Stable Incomplete Multi-view Clustering, Shengju Yu, Dong Zhibin, Siwei Wang, Xinhang Wan, Yue Liu, Weixuan Liang, Pei Zhang, Wenxuan Tu, Xinwang Liu^#, ICML 2024 (spotlight). PDF
• Scalable Incomplete Multi-View Clustering with Structure Alignment, Yi Wen, Siwei Wang^#, Ke Liang, Weixuan Liang, Xinhang Wan, Xinwang Liu^#, Suyuan Liu, Jiyuan Liu, and En Zhu, ACM MM 2023. Code PDF
• Efficient Multi-View Graph Clustering with Local and Global Structure Preservation, Yi Wen^*, Suyuan Liu^*, Xinhang Wan, Siwei Wang, Ke Liang, Xinwang Liu^#, Xihong Yang, Pei Zhang, ACM MM 2023. Code PDF
• Unpaired Multi-View Graph Clustering with Cross-View Structure Matching, Yi Wen, Siwei Wang, Qing Liao, Weixuan Liang, Ke Liang, Xinhang Wan, Xinwang Liu^#, IEEE-TNNLS.Code PDF

🎖 Honors and Awards

• 2023.01 Outstanding Student, National University of Defense Technology. (校优秀学员，top 1%)
• 2022.10 National scholarship, National University of Defense Technology. (研究生国家奖学金)
• 2022.10 Fifth in the 100m at the School sports meeting, National University of Defense Technology. (校运会100m第五名)
• 2022.05 Member of the College Basketball Team, National University of Defense Technology.(学院篮球队队员)
• 2021.06 Excellent Graduated Graduate Student of Northeastern University.(校优秀毕业生)
• 2019.10 Outstanding CLP member, Northeastern University. (校优秀团员标兵)
• 2018.10 Outstanding Student, Northeastern University. (校优秀学生)
• 2018.10 Eighth place in Rope Skipping at the School sports meeting, Northeastern University. (校运会跳绳第八名)

📖 Educations

• 2023.02 - now, Ph.D student, National University of Defense Technology, Changsha, China.
• 2021.09 - 2023.01, Master, National University of Defense Technology, Changsha, China.
• 2017.09 - 2021.06, Undergraduate, Northeastern University, Shenyang, China.
• 2014.09 - 2017.06, Xiangyang No.5 Middle School, Xiangyang, China.

✉ Services

• Journal Reviewer: IEEE Transactions on Knowledge and Data Engineering (TKDE), Neurocomputing.
• Conference Reviewer: NeurIPS 2024, KDD 2024, AAAI 2024, ACM MM 2023.
• Class Monitor (院学生骨干、班长)