The issue of distribution shifts is emerging as a critical concern in graph representation
learning. From the perspective of invariant learning and stable learning, a recently well …

Learning representations on large-sized graphs is a long-standing challenge due to the inter-
dependence nature involved in massive data points. Transformers, as an emerging class of …

Real-world data generation often involves complex inter-dependencies among instances,
violating the IID-data hypothesis of standard learning paradigms and posing a challenge for …

We tackle the problem of graph out-of-distribution (OOD) generalization. Existing graph OOD
algorithms either rely on restricted assumptions or fail to exploit environment information in …

Graph neural networks (GNNs) are widely used in machine learning for graph-structured
data. Even though GNNs have achieved remarkable success in real-world applications …

With the prosperity of contrastive learning for visual representation learning (VCL), it is also
adapted to the graph domain and yields promising performance. However, through a …

Graph neural networks (GNNs) are effective machine learning models for many graph-
related applications. Despite their empirical success, many research efforts focus on the …

Graph structure learning is a well-established problem that aims at optimizing graph
structures adaptive to specific graph datasets to help message passing neural networks (ie …

Unsupervised Graph Domain Adaptation (UGDA) aims to transfer knowledge from a labelled
source graph to an unlabelled target graph in order to address the distribution shifts …

Traffic time series anomaly detection has been intensively studied for years because of its
potential applications in intelligent transportation. However, classical traffic anomaly …