Lots of learning tasks require dealing with graph data which contains rich relation
information among elements. Modeling physics systems, learning molecular fingerprints …

Graph neural networks have emerged as a leading architecture for many graph-level tasks,
such as graph classification and graph generation. As an essential component of the …

Recently, transformer architectures for graphs emerged as an alternative to established
techniques for machine learning with graphs, such as (message-passing) graph neural …

Interpretable graph learning is in need as many scientific applications depend on learning
models to collect insights from graph-structured data. Previous works mostly focused on …

Graph representation learning has shown effectiveness when testing and training graph
data come from the same distribution, but most existing approaches fail to generalize under …

Intrinsic interpretability of graph neural networks (GNNs) is to find a small subset of the input
graph's features--rationale--which guides the model prediction. Unfortunately, the leading …

Financial time series analysis plays a central role in hedging market risks and optimizing
investment decisions. This is a challenging task as the problems are always accompanied …

In recent years, prompt tuning has sparked a research surge in adapting pre-trained models.
Unlike the unified pre-training strategy employed in the language field, the graph field …

In the last few years, graph neural networks (GNNs) have become the standard toolkit for
analyzing and learning from data on graphs. This emerging field has witnessed an extensive …

Graph-level anomaly detection (GLAD) aims to identify graphs that exhibit notable
dissimilarity compared to the majority in a collection. However, current works primarily focus …