Despite the remarkable accomplishments of graph neural networks (GNNs), they
typically rely on task-specific labels, posing potential challenges in terms of
their acquisition. Existing work have been made to address this issue through
the lens of unsupervised domain adaptation, wherein labeled source graphs are
utilized to enhance the learning process for target data. However, the
simultaneous exploration of graph topology and reduction of domain disparities
remains a substantial hurdle. In this paper, we introduce the Dual Adversarial
Graph Representation Learning (DAGRL), which explore the graph topology from
dual branches and mitigate domain discrepancies via dual adversarial learning.
Our method encompasses a dual-pronged structure, consisting of a graph
convolutional network branch and a graph kernel branch, which enables us to
capture graph semantics from both implicit and explicit perspectives. Moreover,
our approach incorporates adaptive perturbations into the dual branches, which
align the source and target distribution to address domain discrepancies.
Extensive experiments on a wild range graph classification datasets demonstrate
the effectiveness of our proposed method.

通过双重对抗学习的方法，本文提出了 Dual Adversarial Graph Representation Learning（DAGRL）来探索图拓扑结构，并且减少域间差异，实验证明了该方法的有效性。