Graph anomaly detection via multi-scale contrastive learning networks with augmented view

J Duan, S Wang, P Zhang, E Zhu, J Hu, H **… - Proceedings of the …, 2023‏ - ojs.aaai.org
Graph anomaly detection (GAD) is a vital task in graph-based machine learning and has
been widely applied in many real-world applications. The primary goal of GAD is to capture …

Graph embedding contrastive multi-modal representation learning for clustering

W **a, T Wang, Q Gao, M Yang… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Multi-modal clustering (MMC) aims to explore complementary information from diverse
modalities for clustering performance facilitating. This article studies challenging problems in …

A Survey of Deep Graph Clustering: Taxonomy, Challenge, Application, and Open Resource

Y Liu, J **a, S Zhou, X Yang, K Liang, C Fan… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Graph clustering, which aims to divide nodes in the graph into several distinct clusters, is a
fundamental yet challenging task. Benefiting from the powerful representation capability of …

Attribute-missing graph clustering network

W Tu, R Guan, S Zhou, C Ma, X Peng, Z Cai… - Proceedings of the …, 2024‏ - ojs.aaai.org
Deep clustering with attribute-missing graphs, where only a subset of nodes possesses
complete attributes while those of others are missing, is an important yet challenging topic in …

Hierarchically contrastive hard sample mining for graph self-supervised pretraining

W Tu, S Zhou, X Liu, C Ge, Z Cai… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Contrastive learning has recently emerged as a powerful technique for graph self-
supervised pretraining (GSP). By maximizing the mutual information (MI) between a positive …

Spatial-spectral graph contrastive clustering with hard sample mining for hyperspectral images

R Guan, W Tu, Z Li, H Yu, D Hu, Y Chen… - … on Geoscience and …, 2024‏ - ieeexplore.ieee.org
Hyperspectral image (HSI) clustering is a fundamental yet challenging task that groups
image pixels with similar features into distinct clusters. Among various approaches …

Self-consistent contrastive attributed graph clustering with pseudo-label prompt

W **a, Q Wang, Q Gao, M Yang… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Attributed graph clustering, which learns node representation from node attribute and
topological graph for clustering, is a fundamental and challenging task for multimedia …

Incomplete graph learning via attribute-structure decoupled variational auto-encoder

X Jiang, Z Qin, J Xu, X Ao - Proceedings of the 17th ACM International …, 2024‏ - dl.acm.org
Graph Neural Networks (GNNs) conventionally operate under the assumption that node
attributes are entirely observable. Their performance notably deteriorates when confronted …

Rare: Robust masked graph autoencoder

W Tu, Q Liao, S Zhou, X Peng, C Ma… - … on Knowledge and …, 2023‏ - ieeexplore.ieee.org
Masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-
training (SGP) paradigm due to its simplicity and effectiveness. However, existing efforts …

Multi-view graph imputation network

X Peng, J Cheng, X Tang, B Zhang, W Tu - Information Fusion, 2024‏ - Elsevier
Graph data in the real world is often accompanied by the problem of missing attributes.
Recently, self-supervised graph representation learning, implementing data imputation …