AGMixup: Adaptive Graph Mixup for Semi-supervised Node Classification

TL;DR

AGMixup introduces an adaptive, subgraph-centric mixup technique for semi-supervised node classification, improving model generalization by better respecting graph topology and pair-specific mixing ratios.

Contribution

It proposes a novel subgraph-based approach and an adaptive mechanism for mixup ratios, addressing limitations of existing graph mixup methods.

Findings

Outperforms state-of-the-art graph mixup methods on seven datasets.

Enhances model generalization and robustness in semi-supervised node classification.

Effectively preserves graph topology during data augmentation.

Abstract

Mixup is a data augmentation technique that enhances model generalization by interpolating between data points using a mixing ratio $\lambda$ in the image domain. Recently, the concept of mixup has been adapted to the graph domain through node-centric interpolations. However, these approaches often fail to address the complexity of interconnected relationships, potentially damaging the graph's natural topology and undermining node interactions. Furthermore, current graph mixup methods employ a one-size-fits-all strategy with a randomly sampled $\lambda$ for all mixup pairs, ignoring the diverse needs of different pairs. This paper proposes an Adaptive Graph Mixup (AGMixup) framework for semi-supervised node classification. AGMixup introduces a subgraph-centric approach, which treats each subgraph similarly to how images are handled in Euclidean domains, thus facilitating a more natural integration of mixup into graph-based learning. We also propose an adaptive mechanism to tune the mixing ratio $\lambda$ for diverse mixup pairs, guided by the contextual similarity and uncertainty of the involved subgraphs. Extensive experiments across seven datasets on semi-supervised node classification benchmarks demonstrate AGMixup's superiority over state-of-the-art graph mixup methods. Source codes are available at \url{https://github.com/WeigangLu/AGMixup}.