English

Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning

Machine Learning 2024-10-10 v1

Abstract

Graph Neural Networks (GNNs) are proficient in graph representation learning and achieve promising performance on versatile tasks such as node classification and link prediction. Usually, a comprehensive hyperparameter tuning is essential for fully unlocking GNN's top performance, especially for complicated tasks such as node classification on large graphs and long-range graphs. This is usually associated with high computational and time costs and careful design of appropriate search spaces. This work introduces a graph-conditioned latent diffusion framework (GNN-Diff) to generate high-performing GNNs based on the model checkpoints of sub-optimal hyperparameters selected by a light-tuning coarse search. We validate our method through 166 experiments across four graph tasks: node classification on small, large, and long-range graphs, as well as link prediction. Our experiments involve 10 classic and state-of-the-art target models and 20 publicly available datasets. The results consistently demonstrate that GNN-Diff: (1) boosts the performance of GNNs with efficient hyperparameter tuning; and (2) presents high stability and generalizability on unseen data across multiple generation runs. The code is available at https://github.com/lequanlin/GNN-Diff.

Keywords

Cite

@article{arxiv.2410.05697,
  title  = {Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning},
  author = {Lequan Lin and Dai Shi and Andi Han and Zhiyong Wang and Junbin Gao},
  journal= {arXiv preprint arXiv:2410.05697},
  year   = {2024}
}
R2 v1 2026-06-28T19:12:28.260Z