Skip to yearly menu bar Skip to main content


Poster

Graph Mixup on Approximate Gromov–Wasserstein Geodesics

Zhichen Zeng · Ruizhong Qiu · Zhe Xu · Zhining Liu · Yuchen Yan · Tianxin Wei · Lei Ying · Jingrui He · Hanghang Tong


Abstract:

Mixup, which generates synthetic training samples on the data manifold, has been shown to be highly effective in augmenting Euclidean data. However, finding a proper data manifold for graph data is non-trivial, as graphs are non-Euclidean data in disparate spaces. Though efforts have been made, most of the existing graph mixup methods neglect the intrinsic geodesic guarantee, thereby generating inconsistent sample-label pairs. To address this issue, we propose GeoMix to mixup graphs on the Gromov-Wasserstein (GW) geodesics. A joint space over input graphs is first defined based on the GW distance, and graphs are then transformed into the GW space through equivalence-preserving transformations. We further show that the linear interpolation of the transformed graph pairs defines a geodesic connecting the original pairs on the GW manifold, hence ensuring the consistency between generated samples and labels. An accelerated mixup algorithm on the approximate low-dimensional GW manifold is further proposed. Extensive experiments show that the proposed GeoMix promotes the generalization and robustness of GNN models.

Live content is unavailable. Log in and register to view live content