171 citations · 207 across the 10 of their papers we have counts for
11 papers
Factorized Neural Operators Decompose Dynamic and Persistent Responses
Hao Tang, Yuechen Duan, Jiongyu Zhu +3
Physical systems often exhibit heterogeneous mechanisms, where rapidly evolving dynamics coexist with persistent structures. Capturing such multiscale physical behavior remains cha…
Geometric Laplace Neural Operator
Hao Tang, Jiongyu Zhu, Zimeng Feng +2
Neural operators have emerged as powerful tools for learning mappings between function spaces, enabling efficient solutions to partial differential equations across varying inputs…
Learning Laplacian Positional Encodings for Heterophilous Graphs
Michael Ito, Jiong Zhu, Dexiong Chen +2
In this work, we theoretically demonstrate that current graph positional encodings (PEs) are not beneficial and could potentially hurt performance in tasks involving heterophilous…
On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks
Jiong Zhu, Gaotang Li, Yao-An Yang +3
Heterophily, or the tendency of connected nodes in networks to have different class labels or dissimilar features, has been identified as challenging for many Graph Neural Network…
Graph Coarsening via Convolution Matching for Scalable Graph Neural Network Training
Charles Dickens, Eddie Huang, Aishwarya Reganti +3
Graph summarization as a preprocessing step is an effective and complementary technique for scalable graph neural network (GNN) training. In this work, we propose the Coarsening Vi…
On Performance Discrepancies Across Local Homophily Levels in Graph Neural Networks
Donald Loveland, Jiong Zhu, Mark Heimann +3
Graph Neural Network (GNN) research has highlighted a relationship between high homophily (i.e., the tendency of nodes of the same class to connect) and strong predictive performan…
Simplifying Distributed Neural Network Training on Massive Graphs: Randomized Partitions Improve Model Aggregation
Jiong Zhu, Aishwarya Reganti, Edward Huang +4
Distributed training of GNNs enables learning on massive graphs (e.g., social and e-commerce networks) that exceed the storage and computational capacity of a single machine. To re…
On Graph Neural Network Fairness in the Presence of Heterophilous Neighborhoods
Donald Loveland, Jiong Zhu, Mark Heimann +3
We study the task of node classification for graph neural networks (GNNs) and establish a connection between group fairness, as measured by statistical parity and equal opportunity…
How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implications
Jiong Zhu, Junchen Jin, Donald Loveland +2
We bridge two research directions on graph neural networks (GNNs), by formalizing the relation between heterophily of node labels (i.e., connected nodes tend to have dissimilar lab…
Graph Neural Networks with Heterophily
Jiong Zhu, Ryan A. Rossi, Anup Rao +4
Graph Neural Networks (GNNs) have proven to be useful for many different practical applications. However, many existing GNN models have implicitly assumed homophily among the nodes…
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
Jiong Zhu, Yujun Yan, Lingxiao Zhao +3
We investigate the representation power of graph neural networks in the semi-supervised node classification task under heterophily or low homophily, i.e., in networks where connect…