4 papers
Accurate and Scalable Graph Neural Networks via Message Invariance
Zhihao Shi, Jie Wang, Zhiwei Zhuang +3
Message passing-based graph neural networks (GNNs) have achieved great success in many real-world applications. For a sampled mini-batch of target nodes, the message passing proces…
Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions
Rui Yang, Jie Wang, Guoping Wu +1
Real-world offline datasets are often subject to data corruptions (such as noise or adversarial attacks) due to sensor failures or malicious attacks. Despite advances in robust off…
Provably Convergent Subgraph-wise Sampling for Fast GNN Training
Jie Wang, Zhihao Shi, Xize Liang +5
Subgraph-wise sampling -- a promising class of mini-batch training techniques for graph neural networks (GNNs -- is critical for real-world applications. During the message passing…
Deep Symbolic Optimization for Combinatorial Optimization: Accelerating Node Selection by Discovering Potential Heuristics
Hongyu Liu, Haoyang Liu, Yufei Kuang +2
Combinatorial optimization (CO) is one of the most fundamental mathematical models in real-world applications. Traditional CO solvers, such as Branch-and-Bound (B&B) solvers, heavi…