GeoMix: Towards Geometry-Aware Data Augmentation
Open Access
- 24 August 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4500-4511
Abstract
Mixup has shown considerable success in mitigating the challenges posed by limited labeled data in image classification. By synthesizing samples through the interpolation of features and labels, Mixup effectively addresses the issue of data scarcity. However, it has rarely been explored in graph learning tasks due to the irregularity and connectivity of graph data. Specifically, in node classification tasks, Mixup presents a challenge in creating connections for synthetic data. In this paper, we propose Geometric Mixup (GeoMix), a simple and interpretable Mixup approach leveraging in-place graph editing. It effectively utilizes geometry information to interpolate features and labels with those from the nearby neighborhood, generating synthetic nodes and establishing connections for them. We conduct theoretical analysis to elucidate the rationale behind employing geometry information for node Mixup, emphasizing the significance of locality enhancement-a critical aspect of our method's design. Extensive experiments demonstrate that our lightweight Geometric Mixup achieves state-of-the-art results on a wide variety of standard datasets with limited labeled data. Furthermore, it significantly improves the generalization capability of underlying GNNs across various challenging out-of-distribution generalization tasks. Our code is available at https://github.com/WtaoZhao/geomix.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networks2023
- GraphMix: Improved Training of GNNs for Semi-Supervised LearningProceedings of the AAAI Conference on Artificial Intelligence, 2021
- Mixup for Node and Graph Classification2021
- Multi-Scale attributed node embeddingJournal of Complex Networks, 2021
- Graph Adversarial Training: Dynamically Regularizing Based on Graph StructureIEEE Transactions on Knowledge and Data Engineering, 2019
- Between-Class Learning for Image Classification2018