High-throughput molecular profiling technologies have produced high-dimensional multi-
omics data, enabling systematic understanding of living systems at the genome scale …

The era of “data deluge” has sparked renewed interest in graph-based learning methods
and their widespread applications ranging from sociology and biology to transportation and …

While graph embedding aims at learning low-dimensional representations of nodes
encompassing the graph topology, word embedding focus on learning word vectors that …

Motivation Biological and cellular systems are often modeled as graphs in which vertices
represent objects of interest (genes, proteins and drugs) and edges represent relational ties …

Heterogeneous graphs are pervasive in practical scenarios, where each graph consists of
multiple types of nodes and edges. Representation learning on heterogeneous graphs aims …

Unsupervised graph-level representation learning has recently shown great potential in a
variety of domains, ranging from bioinformatics to social networks. Plenty of graph …

In classical graph signal processing (GSP), the underlying topological structures are
restricted in terms of dimensionality. A graph or a 1-complex is a combinatorial object that …

A variety of real-world applications require the modeling and the simulation of dynamical
systems, eg, physics, transportation and climate. With the increase of complexity, it becomes …

Many real-world systems such as social networks and moving planets are dynamic in
nature, where a set of coupled objects are connected via the interaction graph and exhibit …

Recent improvements in the performance of state-of-the-art (SOTA) methods for Graph
Representational Learning (GRL) have come at the cost of significant computational …