GraphBench: Next-generation graph learning benchmarking
By: Timo Stoll , Chendi Qian , Ben Finkelshtein and more
Potential Business Impact:
Makes computer learning on networks faster and fairer.
Machine learning on graphs has recently achieved impressive progress in various domains, including molecular property prediction and chip design. However, benchmarking practices remain fragmented, often relying on narrow, task-specific datasets and inconsistent evaluation protocols, which hampers reproducibility and broader progress. To address this, we introduce GraphBench, a comprehensive benchmarking suite that spans diverse domains and prediction tasks, including node-level, edge-level, graph-level, and generative settings. GraphBench provides standardized evaluation protocols -- with consistent dataset splits and performance metrics that account for out-of-distribution generalization -- as well as a unified hyperparameter tuning framework. Additionally, we benchmark GraphBench using message-passing neural networks and graph transformer models, providing principled baselines and establishing a reference performance. See www.graphbench.io for further details.
Similar Papers
DHG-Bench: A Comprehensive Benchmark on Deep Hypergraph Learning
Machine Learning (CS)
Tests computer programs that understand complex groups.
GraphNet: A Large-Scale Computational Graph Dataset for Tensor Compiler Research
Machine Learning (CS)
Makes computer programs run much faster and correctly.
LeMat-GenBench: A Unified Evaluation Framework for Crystal Generative Models
Machine Learning (CS)
Helps find new materials faster and better.