Adversarially Regularized Graph Attention Networks for Inductive Learning on Partially Labeled Graphs

TL;DR

This paper introduces an adversarially regularized graph attention network designed for inductive learning on partially labeled graphs, effectively classifying new nodes without requiring full graph information during training.

Contribution

It proposes a novel attention-based aggregator combined with adversarial training to improve robustness and enable inductive learning on dynamic, partially labeled graphs.

Findings

Outperforms state-of-the-art methods on real-world datasets.

Effectively classifies newly added nodes in dynamic graphs.

Enhances model robustness through adversarial regularization.

Abstract

The high cost of data labeling often results in node label shortage in real applications. To improve node classification accuracy, graph-based semi-supervised learning leverages the ample unlabeled nodes to train together with the scarce available labeled nodes. However, most existing methods require the information of all nodes, including those to be predicted, during model training, which is not practical for dynamic graphs with newly added nodes. To address this issue, an adversarially regularized graph attention model is proposed to classify newly added nodes in a partially labeled graph. An attention-based aggregator is designed to generate the representation of a node by aggregating information from its neighboring nodes, thus naturally generalizing to previously unseen nodes. In addition, adversarial training is employed to improve the model's robustness and generalization ability by enforcing node representations to match a prior distribution. Experiments on real-world datasets demonstrate the effectiveness of the proposed method in comparison with the state-of-the-art methods. The code is available at https://github.com/JiarenX/AGAIN.