In this paper, we study semi-supervised graph classification, a fundamental problem in data
mining and machine learning. The problem is typically solved by learning graph neural …

Graph neural networks have pushed state-of-the-arts in graph classifications recently.
Typically, these methods are studied within the context of supervised end-to-end training …

Hypergraph Convolutional Network (HCN) has be-come a proper choice for capturing high-
order relationships. Existing HCN methods are tailored for static hypergraphs, which are …

As many data in practical applications occur or can be arranged in multiview forms,
multiview clustering utilizing certain complementary and heterogeneous information in …

Multiview clustering has attracted significant attention in various fields, due to the superiority
in mining patterns of multiview data. However, previous methods are still confronted with two …

Multi-view clustering (MVC) utilizes the consistency of multiple views to learn a consensus
representation. However, the existing MVC methods usually use only a single metric to learn …

Graph contrastive learning (GCL) has gained increasing interest as a solution for graph
representation learning. In GCL, graph augmentation is essential to generate contrastive …

Interpreting model behavior is crucial for model evaluation and optimization. Recent
research demonstrates that incorporating human intelligence into the learning process …

Graph clustering is a central topic in unsupervised learning with a multitude of practical
applications. In recent years, multi-view graph clustering has gained a lot of attention for its …

Automatic constraint discovery from a relational database is beneficial for domain experts in
fraud detection and intelligent auditing. Its objective is to discover a set of inherent …