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

ICLR 2026 Conference Submission16401 Authors

Keywords: Graph Neural Networks, Data Augmentation, Mixup, Graph Classification, Graph Edit Distance, Representation Learning, Evaluation

TL;DR: We investigate graph mixup and analyze prediction performance as well as interpolation properties of prior methods empirically.

Abstract:

Mixup is a widely used data augmentation technique that constructs new training
examples by interpolating between existing ones. While effective in domains like
vision and language, applying mixup to graph data is challenging. In this paper, we
analyze and empirically explore state-of-the-art graph mixup methods. We conducted an
independent evaluation following established evaluation protocols for graph
classification and found that none of the 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) that mixup methods that interpolated well often outperform
methods that did not, (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.

Primary Area: learning on graphs and other geometries & topologies

Submission Number: 16401