Deep Learning on Graphs
I focus on advancing graph neural network (GNN) architectures and improving the expressiveness, scalability, interpretability and robustness of GNNs.
ICML 2022LA-GNN is a general pre-training framework that improves GNN performance through augmentation.
ICLR 2021GNNs can learn to execute graph algorithms.
AAAI 2021ID-GNN improves the expressiveness of GNN by considering node identities.
NeurIPS 2017GraphSAGE is a general GNN framework for large-scale graph learning.
ICML 2018GraphRNN is one of the first graph generative models for learning distribution of graphs.
NeurIPS 2019The first framework to explain predictions made by GNNs!