Gaussian Mixture Models Based Augmentation Enhances GNN Generalization

Yassine ABBAHADDOU, Fragkiskos D. Malliaros, Johannes F. Lutzeyer, Amine M. Aboussalah, Michalis Vazirgiannis

Keywords: Graph Neural Networks, Data Augmentation

Abstract: Graph Neural Networks (GNNs) have shown great promise in many learning tasks, notably including node and graph classification, but they face difficulties when tested on new or unseen data. These challenges are exacerbated when training data is limited in size or diversity. To address this issue, we introduce a theoretical framework using Rademacher complexity to compute a regret bound on the generalization error and then characterize the effect of data augmentation. This framework informs the design of GMM-GDA, a new, efficient graph data augmentation (GDA) algorithm leveraging the capability of Gaussian Mixture Models (GMMs) to approximate any distribution. Our approach not only outperforms existing augmentation techniques but also offers improved time complexity, making it highly suitable for real-world applications.

Primary Area: learning on graphs and other geometries & topologies

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 12090