PhD Thesis Proposal - Ta-Yang Wang

Title: Training Heterogeneous Graph Neural Networks using Bandit Sampling        
 
Presenter: Ta-Yang Wang        
 
Time: May 1st, 3:00 PM - 4:00 PM          
 
Location: EEB 219         
 
Committee members: Viktor Prasanna (chair), Jyotirmoy Deshmukh, Rajgopal Kannan, Aiichiro Nakano, and Cauligi Raghavendra        
 
Abstract: Graph neural networks (GNNs) have gained significant attention across diverse areas due to their superior performance in learning graph representations. While GNNs exhibit superior performance compared to other methods, they are primarily designed for homogeneous graphs, where all nodes and edges are of the same type. Training a GNN model for large-scale graphs incurs high computation and storage costs, especially when considering the heterogeneous structural information of each node. To address the demand for efficient GNN training, various sampling methods have been proposed. In this proposal, we hypothesize that one can improve the training efficiency via bandit sampling, an online learning algorithm with provable convergence under weak assumptions on the learning objective. The main idea is to prioritize node types with more informative connections with respect to the learning objective. Additionally, we analyze the limitations of the framework, thus advancing its applicability in large-scale graph learning tasks.

Location: Hughes Aircraft Electrical Engineering Center (EEB) - 219

Audiences: Everyone Is Invited

Contact: Ellecia Williams