Learning to predict missing links is important for many graph-based applications. Existing
methods were designed to learn the association between observed graph structure and …

Despite recent successes, most contrastive self-supervised learning methods are domain-
specific, relying heavily on data augmentation techniques that require knowledge about a …

We present a unified and flexible framework to address the generalized problem of 3D
motion synthesis that covers the tasks of motion prediction, completion, interpolation, and …

Graph machine learning has been extensively studied in both academia and industry.
Although booming with a vast number of emerging methods and techniques, most of the …

Abstract Graph Contrastive Learning (GCL) has emerged to learn generalizable
representations from contrastive views. However, it is still in its infancy with two concerns: 1) …

Abstract Temporal Graph Networks (TGNs) are powerful on modeling temporal graph data
based on their increased complexity. Higher complexity carries with it a higher risk of …

Graph neural networks (GNNs) are widely used for modelling graph-structured data in
numerous applications. However, with their inherently finite aggregation layers, existing …

Rationale is defined as a subset of input features that best explains or supports the
prediction by machine learning models. Rationale identification has improved the …

Abstract Graph Convolutional Networks (GCNs) have shown promising results in modeling
graph-structured data. However, they have difficulty with processing digraphs because of …

Data augmentation helps neural networks generalize better by enlarging the training set, but
it remains an open question how to effectively augment graph data to enhance the …