Xihong Yang

Xihong Yang (杨希洪) 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). His research interests include graph neural networks, semi-supervised learning and self-supervised learning.

Email  /  Google Scholar  /  Github  / 

• [2024.01] Two paper has been accepted by TKDD 2024.
• [2024.01] One papers have been accepted by IEEE TNNLS 2024.
• [2023.12] Two papers have been accepted by AAAI 2024.
• [2023.12] One papers have been accepted by ICDE 2024.
• [2023.07] Five papers have been accepted by ACM MM 2023.
• [2023.07] One paper has been accepted by IEEE TNNLS.
• [2023.06] One paper has been accepted by IEEE TKDE.
• [2023.04] One paper has been accepted by ICML 2023.
• [2023.04] One paper has been accepted by IEEE TNNLS.
• [2023.04] One paper has been accepted by IEEE TAI.
• [2022.12] I won China National Scholarship for graduate students.
• [2022.11] Two papers have been accepted by AAAI 2023.
• [2022.06] One paper has been accepted by IEEE TNNLS 2022.
• [2021.12] One paper has been accepted by AAAI 2022.
• [2020.12] I won China National Scholarship for undergraduate students.

My research interests include self-supervised learning, graph representation learning, deep graph clustering, and multi-view representation learning. The representative papers are highlighted.

In our method, we improve the discriminative capability of the latent embeddings by an interpolation based augmentation strategy and a correlation reduction mechanism.

We propose a novel CONtrastiVe Graph ClustEring network with Reliable AugmenTation (COVERT)

We propose a novel Dual contrastive calibration network for Multi-View Clustering (DealMVC).

We propose a novel anchor-based multi-view graph clustering framework with Local and Global Structure Preservation, termed EMVGC-LG.

We propose an effective method called Topological Structure Learning (TSL).

We analyze drawbacks of the exising deep graph clustering methods and scale deep graph clustering to large-scale graphs. The proposed shrink and dilation loss functions optimize clustering distribution adversarially, allowing batch training without performance dropping.

We propose to replace the complicated and consuming graph data augmentations by designing the parameter un-shared siamese encoders and perurbing the node embeddings.

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.

Contrastive deep Graph Clustering network (CCGC) is proposed by mining the intrinsic supervision information in the high-confidence clustering results.

Deep graph clustering, which aims to group the nodes in graph into disjoint clusters, has become a new hot research spot. This paper summarizes the taxonomy, challenge, and application of deep graph clustering. We hope this work will serve as a quick guide and help researchers to overcome the challenges in this field.

We (1) propose an interpolation-based method to construct more reliable positive sample pairs; (2) design a novel contrastive loss to guide the embedding of the learned network to change linearly between samples so as to improve the discriminative capability of the network by enlarging the margin decision boundaries.

We propose a self-supervised deep graph clustering method termed Dual Correlation Reduction Network (DCRN) to address the representation collapse issue by reducing information correlation in both sample and feature levels.