News
- [2024.07] One paper has been accepted by IEEE TNNLS.
- [2024.05] One paper has been accepted by IEEE TNNLS.
- [2024.03] I serve as a reviewer for IEEE TPAMI.
- [2024.01] One paper has been accepted by IEEE TKDE.
- [2023.09] I am visiting A*STAR for 18 months.
- [2023.07] I was awarded CSC Scholarship.
- [2023.04] One paper has been accepted by IEEE TNNLS.
- [2023.04] One paper has been accepted by IEEE TKDE.
- [2022.11] Two papers have been accepted by AAAI 2023.
- [2022.10] I won the China National Scholarship (top 0.2%).
- [2022.06] One paper has been accepted by ACMMM 2022.
- [2022.06] One paper has been accepted by IEEE TNNLS.
- [2021.12] I won the first prize of postgraduate academic scholarship at NUDT.
- [2020.10] I won the China National Scholarship (top 0.2%).
- [2020.10] I won the first prize of postgraduate academic scholarship at NUDT.
|
Research
Representative papers are highlighted.
|
|
Generalized ab Initio Refinement for Multi-view Bipartite Graph Clustering
Liang Li,
Yuangang Pan,
Jie Liu,
Xinwang Liu,
Kenli Li,
Keqin Li
Preprint , 2024
Paper
/
Code
We propose a reinforced multi-view bipartite graph clustering.
|
|
Jet-BGC: Joint Latent Embedding and Structural Fusion Bipartite Graph Clustering
Liang Li,
Jie Liu,
Xinwang Liu,
Kenli Li,
Keqin Li
Preprint , 2023
[IEEE Xplore]
/
[pdf]
/
[Code]
We propose a novel Jet-BGC model that integrating embedding learning and Structural Fusion.
|
|
BGAE: Auto-encoding Multi-view Bipartite Graph Clustering
Liang Li,
Yuangang Pan,
Jie Liu,
Yue Liu,
Xinwang Liu,
Kenli Li,
Ivor W. Tsang,
Keqin Li
IEEE TKDE (CCF-A, IF: 8.9), 2024
[IEEE Xplore]
/
[pdf]
/
[Code]
We rethink existing paradigms and find that a common design is to construct the bipartite graph directly from the input data,
i.e. only consider the unidirectional "encoding" process. Inspired by the popular "encoding-decoding" design in deep learning,
we transfer it into graph machine learning and propose a novel model.
|
|
Multi-view Bipartite Graph Clustering with Coupled Noisy Feature Filter
Liang Li,
Junpu Zhang,
Siwei Wang,
Xinwang Liu,
Kenli Li,
Keqin Li
IEEE TKDE (CCF-A, IF: 8.9), 2023
[IEEE Xplore]
/
[pdf]
/
[Code]
One crucial finding is that the existence of noisy features will incur "anchor shift",
which deviates from the potential centroids.
We propose a novel noisy feature filter mechanism to remedy the anchor shift,
and we theoretically analyze the bounds of the bipartite graph's sparsity.
|
|
Multiple Kernel Clustering with Dual Noise Minimization
Junpu Zhang,
Liang Li (Co-first author),
Siwei Wang,
Jiyuan Liu,
Yue Liu,
Xinwang Liu,
En Zhu,
ACM MM (CCF-A), 2022
[Link]
/
[pdf]
/
[Code]
We mathematically disassemble the noise within kernel partition into dual noise,
namely, Null space noise (N-noise) and Column space noise (C-noise),
and propose an elegant method to minimize them. We observe that dual noise will pollute the block diagonal structures. An interesting finding is that C-noise exhibits stronger destruction than N-noise.
|
|
Local Sample-Weighted Multiple Kernel Clustering With Consensus Discriminative Graph
Liang Li,
Siwei Wang,
Xinwang Liu,
En Zhu,
Li Shen,
Kenli Li,
Keqin Li
IEEE TNNLS (CCF-B, IF: 10.4), 2022
[IEEE Xplore]
/
[pdf]
/
[Code]
We investigate an important issue that how to localize the kernel matrix in multi-kernel clustering. Compared to the traditional KNN manner that neglects the ranking relationship of neighbors, this paper proposes a novel localized MKC algorithm coupled flexible graph learning, termd LSWMKC, which achieves fully exploring the latent local manifold.
|
|
TFMKC: Tuning-free Multiple Kernel Clustering Coupled with Diverse Partition Fusion
Junpu Zhang,
Liang Li(Co-first author),
Xinwang Liu
IEEE TNNLS (CCF-B, IF: 10.4) , 2024
[IEEE Xplore]
/
[pdf]
/
[Code]
We propose an elegant diverse kernel partition fusion framework to get the optimal partition.
|
|
Improved Dual Correlation Reduction Network
Yue Liu,
Sihang Zhou,
Xihong Yang,
Xinwang Liu,
Wenxuan Tu,
Liang Li,
Xin Xu,
Fuchun Sun,
IEEE T-NNLS(CCF-B, IF: 10.4), 2024
[IEEE Xplore]
/
[pdf]
/
[Code]
/
We explore deep-in reasons of representation collapse in deep graph clustering and improve the dual correlation reduction network with the affinity recovery strategy.
|
|
Simple Contrastive Graph Clustering
Yue Liu,
Xihong Yang,
Sihang Zhou,
Xinwang Liu,
Siwei Wang,
Ke Liang,
Wenxuan Tu,
Liang Li,
IEEE TNNLS (CCF-B, IF: 10.4), 2023
[IEEE Xplore]
/
[pdf]
/
[Code]
We propose to replace the complicated and consuming graph data augmentations by designing the parameter un-shared siamese encoders and perurbing the node embeddings.
|
|
Hard Sample Aware Network for Contrastive Deep Graph Clustering
Yue Liu,
Xihong Yang,
Sihang Zhou,
Xinwang Liu,
Z. Wang,
Ke Liang,
Wenxuan Tu,
Liang Li ,
Jingcan Duan,
Cancan Chen
AAAI (CCF-A, Oral presentation), 2023
[Link]
/
[pdf]
/
[Code]
We propose Hard Sample Aware Network (HSAN) to mine both the hard positive samples and hard negative samples with a comprehensive similarity measure criterion and a general dynamic sample weighing strategy.
|
|
Let the data choose: Flexible and Diverse Anchor Graph Fusion for Scalable Multi-view Clustering
Pei Zhang,
Siwei Wang,
Liang Li,
Changwang. Zhang,
Xinwang Liu,
En Zhu,
Zhe Liu,
Lu Zhou,
Lei Luo,
AAAI (CCF-A), 2023
[Link]
/
[pdf]
/
[Code]
We propose to fuse diverse bipartite graphs across multiple views that can avoid tune the anchor number manually.
|
- Reviewer for TPAMI, TKDE, JAIR, TNNLS, TBD, ACM TOMM, Neurocomputing, DSP
- Reviewer for NeurIPS24, ICLR25, AITATS25, ACM MM24/23, AAAI24/23, PRCV22
- CSC Scholarship, 2023.
- National Scholarship, 2022.
- First Prize of Postgraduate Academic Scholarship, 2021.
- National Scholarship, 2020.
- First Prize of Postgraduate Academic Scholarship, 2020.
- Postgraduate Scientific Research Innovation Project of Hunan Province (CX20200008, CX20200084), 2020.
- Second Prize of "HUAWEI" the 16th China Post-Graduate Mathematical Contest in Modeling, 2019.
- Excellent Graduated Graduate Student, HUST, 2018.
- Recommendation for admission to NUDT, 2018.
Design and source code from Jon Barron's website
|