The next statistics seminar will be presented by Prof Junbin Gao from the Business School.
Title: Design Your Own Universe: A Physics-Informed Agnostic Method for Enhancing Graph Neural Networks
Speaker: Junbin Gao
Time and location : 1-2pm on Carslaw 275 or Zoom
Abstract : Physics-informed Graph Neural Networks have achieved remarkable performance in learning through graph-structured data by mitigating common GNN challenges such as over-smoothing, over-squashing, and heterophily adaption. Despite these advancements, the development of a simple yet effective paradigm that appropriately integrates previous methods for handling all these challenges is still underway. In this talk, I will draw an analogy between the propagation of GNNs and particle systems in physics, proposing a model-agnostic enhancement framework. This framework enriches the graph structure by introducing additional nodes and rewiring connections with both positive and negative weights, guided by node labeling information. Empirical validations on benchmarks for homophilic, heterophilic graphs, and long-term graph datasets show that GNNs enhanced by our method significantly outperform their original counterparts.