Transfer learning on graphs drawn from varied distributions (domains) is in great demand
across many applications. Emerging methods attempt to learn domain-invariant …

Abstract Existing Optimal Transport (OT) methods mainly derive the optimal transport
plan/matching under the criterion of transport cost/distance minimization, which may cause …

In recent years, graph pre-training has gained significant attention, focusing on acquiring
transferable knowledge from unlabeled graph data to improve downstream performance …

In recent years, remarkable achievements have been made in artificial intelligence tasks
and applications based on deep neural networks (DNNs), especially in the fields of vision …

Molecular representation learning has shown great success in advancing AI-based drug
discovery. A key insight of many recent works is that the 3D geometric structure of molecules …

Recently, the paradigm of pre-training and fine-tuning graph neural networks has been
intensively studied and applied in a wide range of graph mining tasks. Its success is …

As an important methodology to measure distribution discrepancy, optimal transport (OT)
has been successfully applied to learn generalizable visual models under changing …

Text documents are often interconnected in a network structure, eg, academic papers via
citations, Web pages via hyperlinks. On the one hand, though Graph Neural Networks …

In recent years, hypergraph learning has attracted great attention due to its capacity in
representing complex and high-order relationships. However, current neural network …

The paradigm of pre-training and fine-tuning graph neural networks has attracted wide
research attention. In previous studies, the pre-trained models are viewed as universally …