Is Graph Mixup Beneficial? Investigating Interpolation And Empirical Performance of Graph Mixup Methods

Simon Forbat, Rainer GemullaSubmission to ICLR 2026 · Rejected

Abstract

Mixup is a widely used data augmentation technique that constructs new training examples by interpolating between existing ones. While simple and effective in domains like vision and language, applying mixup to graph data is non-trivial and independent empirical evidence for its effectiveness is lacking. To fill this gap, we conducted an independent evaluation following established evaluation protocols for graph classification and found that none of the state-of-the-art mixup methods yielded statistically significant improvements over the no-mixup baseline. To obtain further insights, we analyzed the graphs generated from existing mixup methods from an interpolation perspective using the graph edit distance. We found that (i) many mixup methods failed to interpolate well, (ii) high interpolation error led to performance degradation, and (iii) even optimal interpolation did not lead to performance improvements. Our findings highlight the need for a more rigorous exploration and evaluation of mixup for graphs.
BibTeX
@inproceedings{forbat2026is,
  author = {Simon Forbat and Rainer Gemulla},
  title = {{Is Graph Mixup Beneficial? Investigating Interpolation And Empirical Performance of Graph Mixup Methods}},
  booktitle = {International Conference on Machine Learning},
  year = {2026},
  url = {https://openreview.net/forum?id=KB9z4bnrbD},
}

Loading related content...

Figure