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

ICLR 2026 Conference Submission19363 Authors

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

TL;DR: We introduce ECHO, a benchmark to evaluate GNNs on long-range propagation. We show that ECHO genuinely require long-range dependencies, and we establish strong baselines to provide a comprehensive reference point for future research.

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, namely 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 two real-world datasets, ECHO-Charge and ECHO-Energy, which define chemically grounded benchmarks for predicting atomic partial charges and molecular total energies, respectively, with reference computations obtained at the density functional theory (DFT) level. Both tasks inherently depend on capturing complex long-range molecular interactions. Our extensive benchmarking of popular GNN architectures reveals clear performance gaps, emphasizing the difficulty of true long-range propagation and highlighting 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.

Primary Area: datasets and benchmarks

Submission Number: 19363