USER: Unsupervised Structural Entropy-based Robust Graph Neural Network

Speaker:

Yifei Wang (Ph.D. student, the University of Auckland)

Time:

16:20-17:20 (Time in Beijing)
21:20-22:20 (Time in Auckland)
April 29, 2022 (Friday)

Venue:

B1-518B, Research Building 4

Abstract:

Today graph neural networks (GNN) are widely used for processing complex graph data. However, GNN models are vulnerable in real-world scenarios as the input graphs are prone to noises, potentially distorting node representations.
I will introduce our work on Structural Entropy-based Robust learning method for Graph Neural Network. We show that by minimizing the structural entropy, the affect of noises in input graphs can be alleviated.