SEAL: Semi-supervised Adversarial Active Learning on Attributed Graphs

TL;DR

SEAL introduces a novel semi-supervised adversarial framework for active learning on attributed graphs, leveraging deep neural networks and a unified scoring strategy to improve label efficiency and performance.

Contribution

The paper proposes a new adversarial active learning framework that jointly learns graph embeddings and a discriminator to select informative nodes more effectively.

Findings

SEAL outperforms state-of-the-art baselines on four real-world networks.

The adversarial approach enhances the informativeness of selected nodes.

The framework effectively integrates embedding and discrimination in a unified process.

Abstract

Active learning (AL) on attributed graphs has received increasing attention with the prevalence of graph-structured data. Although AL has been widely studied for alleviating label sparsity issues with the conventional non-related data, how to make it effective over attributed graphs remains an open research question. Existing AL algorithms on graphs attempt to reuse the classic AL query strategies designed for non-related data. However, they suffer from two major limitations. First, different AL query strategies calculated in distinct scoring spaces are often naively combined to determine which nodes to be labelled. Second, the AL query engine and the learning of the classifier are treated as two separating processes, resulting in unsatisfactory performance. In this paper, we propose a SEmi-supervised Adversarial active Learning (SEAL) framework on attributed graphs, which fully leverages the representation power of deep neural networks and devises a novel AL query strategy in an adversarial way. Our framework learns two adversarial components: a graph embedding network that encodes both the unlabelled and labelled nodes into a latent space, expecting to trick the discriminator to regard all nodes as already labelled, and a semi-supervised discriminator network that distinguishes the unlabelled from the existing labelled nodes in the latent space. The divergence score, generated by the discriminator in a unified latent space, serves as the informativeness measure to actively select the most informative node to be labelled by an oracle. The two adversarial components form a closed loop to mutually and simultaneously reinforce each other towards enhancing the active learning performance. Extensive experiments on four real-world networks validate the effectiveness of the SEAL framework with superior performance improvements to state-of-the-art baselines.