GraphBench: Next-generation graph learning benchmarking

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Stoll, Timo, Qian, Chendi, Finkelshtein, Ben, Parviz, Ali, Weber, Darius, Frasca, Fabrizio, Shavit, Hadar, Siraudin, Antoine, Mielke, Arman, Anastacio, Marie, Müller, Erik, Bechler-Speicher, Maya, Bronstein, Michael, Galkin, Mikhail, Hoos, Holger, Niepert, Mathias, Perozzi, Bryan, Tönshoff, Jan, Morris, Christopher
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910203916582912
author Stoll, Timo
Qian, Chendi
Finkelshtein, Ben
Parviz, Ali
Weber, Darius
Frasca, Fabrizio
Shavit, Hadar
Siraudin, Antoine
Mielke, Arman
Anastacio, Marie
Müller, Erik
Bechler-Speicher, Maya
Bronstein, Michael
Galkin, Mikhail
Hoos, Holger
Niepert, Mathias
Perozzi, Bryan
Tönshoff, Jan
Morris, Christopher
author_facet Stoll, Timo
Qian, Chendi
Finkelshtein, Ben
Parviz, Ali
Weber, Darius
Frasca, Fabrizio
Shavit, Hadar
Siraudin, Antoine
Mielke, Arman
Anastacio, Marie
Müller, Erik
Bechler-Speicher, Maya
Bronstein, Michael
Galkin, Mikhail
Hoos, Holger
Niepert, Mathias
Perozzi, Bryan
Tönshoff, Jan
Morris, Christopher
contents Machine learning on graphs has made substantial progress across domains such as molecular property prediction and chip design. Yet benchmarking practices remain fragmented, often relying on narrow, task-specific datasets and inconsistent evaluation protocols, hindering reproducibility and broader progress. With the recent popularity of graph foundation models, these weaknesses have become apparent, as existing benchmarks are insufficient for thorough evaluation. To address these challenges, we introduce GraphBench, a comprehensive benchmark suite spanning diverse real-world domains and task settings, including node-level, edge-level, graph-level, and generative tasks. GraphBench provides standardized evaluation protocols, including consistent dataset splits and metrics for assessing out-of-distribution generalization across selected tasks, as well as a unified hyperparameter-tuning framework. We further evaluate GraphBench with recent message-passing neural networks and graph transformer models, establishing principled baselines for future research. See www.graphbench.io for further details.
format Preprint
id arxiv_https___arxiv_org_abs_2512_04475
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GraphBench: Next-generation graph learning benchmarking
Stoll, Timo
Qian, Chendi
Finkelshtein, Ben
Parviz, Ali
Weber, Darius
Frasca, Fabrizio
Shavit, Hadar
Siraudin, Antoine
Mielke, Arman
Anastacio, Marie
Müller, Erik
Bechler-Speicher, Maya
Bronstein, Michael
Galkin, Mikhail
Hoos, Holger
Niepert, Mathias
Perozzi, Bryan
Tönshoff, Jan
Morris, Christopher
Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
Machine learning on graphs has made substantial progress across domains such as molecular property prediction and chip design. Yet benchmarking practices remain fragmented, often relying on narrow, task-specific datasets and inconsistent evaluation protocols, hindering reproducibility and broader progress. With the recent popularity of graph foundation models, these weaknesses have become apparent, as existing benchmarks are insufficient for thorough evaluation. To address these challenges, we introduce GraphBench, a comprehensive benchmark suite spanning diverse real-world domains and task settings, including node-level, edge-level, graph-level, and generative tasks. GraphBench provides standardized evaluation protocols, including consistent dataset splits and metrics for assessing out-of-distribution generalization across selected tasks, as well as a unified hyperparameter-tuning framework. We further evaluate GraphBench with recent message-passing neural networks and graph transformer models, establishing principled baselines for future research. See www.graphbench.io for further details.
title GraphBench: Next-generation graph learning benchmarking
topic Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
url https://arxiv.org/abs/2512.04475