1 code implementation • 24 Dec 2023 • Charles Dickens, Eddie Huang, Aishwarya Reganti, Jiong Zhu, Karthik Subbian, Danai Koutra
Notably, CONVMATCH achieves up to 95% of the prediction performance of GNNs on node classification while trained on graphs summarized down to 1% the size of the original graph.
no code implementations • 8 Jun 2023 • Donald Loveland, Jiong Zhu, Mark Heimann, Benjamin Fish, Michael T. Schaub, Danai Koutra
We ground the practical implications of this work through granular analysis on five real-world datasets with varying global homophily levels, demonstrating that (a) GNNs can fail to generalize to test nodes that deviate from the global homophily of a graph, and (b) high local homophily does not necessarily confer high performance for a node.
1 code implementation • 17 May 2023 • Jiong Zhu, Aishwarya Reganti, Edward Huang, Charles Dickens, Nikhil Rao, Karthik Subbian, Danai Koutra
Backed by our theoretical analysis, instead of maximizing the recovery of cross-instance node dependencies -- which has been considered the key behind closing the performance gap between model aggregation and centralized training -- , our framework leverages randomized assignment of nodes or super-nodes (i. e., collections of original nodes) to partition the training graph such that it improves data uniformity and minimizes the discrepancy of gradient and loss function across instances.
no code implementations • 10 Jul 2022 • Donald Loveland, Jiong Zhu, Mark Heimann, Ben Fish, Michael T. Schaub, Danai Koutra
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, and local assortativity, i. e., the tendency of linked nodes to have similar attributes.
1 code implementation • 14 Jun 2021 • Jiong Zhu, Junchen Jin, Donald Loveland, Michael T. Schaub, Danai Koutra
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 labels) and the robustness of GNNs to adversarial attacks.
1 code implementation • 28 Sep 2020 • Jiong Zhu, Ryan A. Rossi, Anup Rao, Tung Mai, Nedim Lipka, Nesreen K. Ahmed, Danai Koutra
Graph Neural Networks (GNNs) have proven to be useful for many different practical applications.
4 code implementations • NeurIPS 2020 • Jiong Zhu, Yujun Yan, Lingxiao Zhao, Mark Heimann, Leman Akoglu, Danai Koutra
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 connected nodes may have different class labels and dissimilar features.