Search Results for author:
Found 7 papers, 5 papers with code
Graph Coarsening via Convolution Matching for Scalable Graph Neural Network Training
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.
On Performance Discrepancies Across Local Homophily Levels in Graph Neural Networks
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.
Simplifying Distributed Neural Network Training on Massive Graphs: Randomized Partitions Improve Model Aggregation
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.
On Graph Neural Network Fairness in the Presence of Heterophilous Neighborhoods
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.
How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implications
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.
Graph Neural Networks with Heterophily
Graph Neural Networks (GNNs) have proven to be useful for many different practical applications.
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
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.
