Pith. sign in

REVIEW 18 cited by

Benchmarking Graph Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2003.00982 v5 pith:75LU6VML submitted 2020-03-02 cs.LG stat.ML

classification cs.LGstat.ML
keywords benchmarkframeworkgnnsgraphbecomefieldgraphsnetworks
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In the last few years, graph neural networks (GNNs) have become the standard toolkit for analyzing and learning from data on graphs. This emerging field has witnessed an extensive growth of promising techniques that have been applied with success to computer science, mathematics, biology, physics and chemistry. But for any successful field to become mainstream and reliable, benchmarks must be developed to quantify progress. This led us in March 2020 to release a benchmark framework that i) comprises of a diverse collection of mathematical and real-world graphs, ii) enables fair model comparison with the same parameter budget to identify key architectures, iii) has an open-source, easy-to-use and reproducible code infrastructure, and iv) is flexible for researchers to experiment with new theoretical ideas. As of December 2022, the GitHub repository has reached 2,000 stars and 380 forks, which demonstrates the utility of the proposed open-source framework through the wide usage by the GNN community. In this paper, we present an updated version of our benchmark with a concise presentation of the aforementioned framework characteristics, an additional medium-sized molecular dataset AQSOL, similar to the popular ZINC, but with a real-world measured chemical target, and discuss how this framework can be leveraged to explore new GNN designs and insights. As a proof of value of our benchmark, we study the case of graph positional encoding (PE) in GNNs, which was introduced with this benchmark and has since spurred interest of exploring more powerful PE for Transformers and GNNs in a robust experimental setting.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 18 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 233 citations worldwide. Full citation record

  1. Primal-Dual Neural Algorithmic Reasoning

    cs.LG 2025-05 conditional novelty 7.0 of 10

    A GNN framework that simulates primal-dual approximation algorithms for NP-hard problems and, with small-instance optimal labels, can beat the algorithm it learns.

  2. Multi-Granularity Position Embedding of Graphs via Granular-Ball for Link Prediction

    cs.SI 2026-07 conditional novelty 6.0 of 10

    MGLP uses granular-ball graph refinement to construct hierarchical landmarks and a depth-weighted distance measure, improving link prediction over single-granularity position embeddings.

  3. Computationally-efficient Graph Modeling with Refined Graph Random Features

    cs.LG 2025-10 conditional novelty 6.0 of 10

    Stitching several short random walks into a product of unbiased feature matrices approximates graph node kernels with less variance and better long-range coverage than single long walks.

  4. GraphPFN: A Prior-Data Fitted Graph Foundation Model

    cs.LG 2025-09 conditional novelty 6.0 of 10

    GraphPFN, a graph foundation model pretrained on synthetic graphs from a stochastic-block-model plus preferential-attachment prior with graph-aware structured causal models, outperforms existing graph foundation model...

  5. SourceDetMamba: A Graph-aware State Space Model for Source Detection in Sequential Hypergraphs

    cs.SI 2025-05 conditional novelty 6.0 of 10

    SourceDetMamba detects rumor sources by feeding reverse-ordered hypergraph snapshots through a Mamba state-space model with a graph-aware state update, and reports large accuracy gains over baselines on eight datasets.

  6. ReFill: Reinforcement Learning for Fill-In Minimization

    cs.LG 2025-01 conditional novelty 6.0 of 10

    A reinforcement learning agent that picks variable elimination orders using graph neural networks slightly reduces fill-in versus minimum degree and minimum fill-in heuristics on small test graphs.

  7. Learning interactions between Rydberg atoms

    quant-ph 2024-12 conditional novelty 6.0 of 10

    A size-invariant graph neural network, trained on small DMRG-simulated Rydberg Ising arrays, predicts atom positions on larger arrays from spin correlators, backed by a bijection theorem between correlations and interactions.

  8. Investigating Graph Neural Networks and Classical Feature-Extraction Techniques in Activity-Cliff and Molecular Property Prediction

    cs.LG 2024-11 conditional novelty 6.0 of 10

    A systematic comparison shows ECFP fingerprints still beat GNNs at standard QSAR prediction, while GIN features and a new frequency-based fingerprint method (Sort & Slice) improve activity-cliff and property prediction.

  9. Few-shot Learning on AMS Circuits and Its Application to Parasitic Capacitance Prediction

    cs.LG 2025-07 conditional novelty 5.0 of 10

    A few-shot graph-pretraining pipeline, built from subgraph sampling and a hybrid graph transformer, predicts parasitic coupling capacitance on unseen AMS circuits with substantially lower error than prior graph baselines.

  10. Towards Foundation Models on Graphs: An Analysis on Cross-Dataset Transfer of Pretrained GNNs

    cs.LG 2024-12 conditional novelty 5.0 of 10

    Pretrained GNN embeddings transfer across molecular graphs only under certain data-regime and feature-similarity conditions, and a proposed feature-structuralization method does not consistently improve transfer.

  11. Cluster-guided Contrastive Class-imbalanced Graph Classification

    cs.LG 2024-12 conditional novelty 5.0 of 10

    C3GNN improves class-imbalanced graph classification by clustering majority classes into balanced subclasses, applying Mixup inside each subclass, and learning with hierarchical supervised contrastive losses.

  12. A Data-Driven Approach to Dataflow-Aware Online Scheduling for Graph Neural Network Inference

    cs.LG 2024-11 conditional novelty 5.0 of 10

    A data-driven framework predicts GNN inference latency for different accelerator dataflows and uses those predictions to schedule jobs, reporting large speedups in simulation.

  13. GraphPPD: Posterior Predictive Modelling for Graph-Level Inference

    stat.ML 2025-08 conditional novelty 4.0 of 10

    A cross-attention context layer on top of graph neural networks yields small accuracy gains and uncertainty estimates for graph-level classification and regression.

  14. sHGCN: Simplified hyperbolic graph convolutional neural networks

    cs.LG 2025-06 conditional novelty 4.0 of 10

    A simplified hyperbolic GCN that avoids redundant log/exp computations is competitive or faster than prior HGCN variants on four benchmark graphs.

  15. GNN-Suite: a Graph Neural Network Benchmarking Framework for Biomedical Informatics

    cs.LG 2025-05 conditional novelty 4.0 of 10

    A new benchmarking framework built on Nextflow shows graph neural networks outperform feature-only logistic regression across four cancer-gene network configurations.

  16. Injecting Knowledge Graphs into Large Language Models

    cs.LG 2025-05 reject novelty 4.0 of 10

    A frozen LLM answers graph reasoning questions when a learned knowledge-graph embedding vector is prepended to the query, outperforming prompting baselines in the reported experiments.

  17. Relational Deep Learning: Challenges, Foundations and Next-Generation Architectures

    cs.LG 2025-06 conditional novelty 3.0 of 10

    A review of Relational Deep Learning that formalizes relational entity graphs, catalogs datasets and methods, and advocates for unified GNN and foundation model research directions.

  18. Learning Causality for Modern Machine Learning

    cs.LG 2025-06 conditional novelty 2.0 of 10

    A thesis compiling six papers that use causal invariance to improve graph neural networks' out-of-distribution generalization, interpretability, and robustness.

Pith tools