mlsanityData to 14 Oct 2026

Graph Contrastive Learning versus Untrained Baselines: The Role of Dataset Size

arXiv 2509.01541 ↗First posted 1 Sep 2025cs.LG cond-mat.softcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph Contrastive Learning (GCL) has emerged as a leading paradigm for self-supervised learning on graphs, with strong performance reported on standardized datasets and growing applications ranging from genomics to drug discovery. We ask a basic question: does GCL actually outperform untrained baselines? We find that GCL's advantage depends strongly on dataset size and task difficulty. On standard datasets, untrained Graph Neural Networks (GNNs), simple multilayer perceptrons, and even handcrafted statistics can rival or exceed GCL. On the large molecular dataset ogbg-molhiv, we observe a crossover: GCL lags at small scales but pulls ahead beyond a few thousand graphs, though this gain eventually plateaus. On synthetic datasets, GCL accuracy approximately scales with the logarithm of the number of graphs and its performance gap (compared with untrained GNNs) varies with respect to task complexity. Moving forward, it is crucial to identify the role of dataset size in benchmarks and applications, as well as to design GCL algorithms that avoid performance plateaus.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 38 references that are in the map. First posted on arXiv 1 Sep 2025.

Builds on

24 of 38 references.

References · 24

  1. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  2. 2018How Powerful are Graph Neural Networks?cited by 4,393
  3. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  4. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  5. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  6. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  7. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  8. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  9. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  10. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  11. 2021Graph Contrastive Learning Automatedcited by 287
  12. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
12 more
  1. 2017graph2vec: Learning Distributed Representations of Graphscited by 230
  2. 2022SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentationcited by 171
  3. 2021An Empirical Study of Graph Contrastive Learningcited by 113
  4. 2025PyG 2.0: Scalable Learning on Real World Graphscited by 52
  5. 2021Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practicescited by 25
  6. 2024TopoGCL: Topological Graph Contrastive Learningcited by 14
  7. 2022Analyzing Data-Centric Properties for Graph Contrastive Learningcited by 7
  8. 2023Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learningcited by 7
  9. 2024Graph Contrastive Learning with Cohesive Subgraph Awarenesscited by 6
  10. 2024Multi-Scale Subgraph Contrastive Learningcited by 5
  11. 2024Rethinking the Effectiveness of Graph Classification Datasets in Benchmarks for Assessing GNNscited by 4
  12. 2025Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negativescited by 1

Built on by

Not cited yet.