Danai Koutra

Simplifying Distributed Neural Network Training on Massive Graphs: Randomized Partitions Improve Model Aggregation

2023 · arXiv (Cornell University)

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 reach performance comparable to centralized training, distributed frameworks focus …

On Performance Discrepancies Across Local Homophily Levels in Graph Neural Networks

2023 · arXiv (Cornell University)

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 performance in node classification. However, recent work has found …

On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks

2024 · arXiv (Cornell University)

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 (GNN) models. While the challenges of applying GNNs …

Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning

2025

Graph machine learning has made significant strides in recent years, yet the integration of visual information with graph structure and its potential for improving performance in downstream tasks remains an underexplored area. To address this …