Can You Hear Me Now? A Benchmark for Long-Range Graph Propagation

Luca Miglior, Matteo Tolloso, Alessio Gravina, Davide Bacciu

Keywords: long-range propagation, graph neural network, benchmark

Abstract: Effectively capturing long-range interactions remains a fundamental yet unresolved challenge in graph neural network (GNN) research, critical for applications across diverse fields of science. To systematically address this, we introduce ECHO (Evaluating Communication over long HOps), a novel benchmark specifically designed to rigorously assess the capabilities of GNNs in handling very long-range graph propagation. ECHO includes three synthetic graph tasks -- single-source shortest paths, node eccentricity, and graph diameter -- each constructed over diverse and structurally challenging topologies intentionally designed to introduce significant information bottlenecks. ECHO also includes a real-world dataset, ECHO-Chem, grounded on a novel chemically-grounded application involving the prediction of atomic partial charges in molecules, which critically depends on the ability to capture intricate long-range molecular interactions. We provide an extensive benchmarking on popular GNN architectures which reveals clear performance gaps, emphasizing the difficulty of true long-range propagation and highlighting models and design choices capable of overcoming inherent limitations. ECHO thereby sets a new standard for evaluating long-range information propagation, also providing a compelling example for its need in AI for science.

Dataset URL: https://huggingface.co/datasets/gmander44/ECHO

Code URL: https://anonymous.4open.science/r/ECHO-benchmarks/

Primary Area: Datasets & Benchmarks illustrating Different Deep learning Scenarios (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 1659