Generative Flow Networks for Precise Reward-Oriented Active Learning on Graphs

TL;DR

This paper introduces GFlowGNN, a novel generative flow network approach for graph active learning that improves exploration and reward alignment, leading to better performance on real datasets.

Contribution

The paper formulates graph active learning as a generative process using flow networks, enhancing exploration and reward proportionality over existing methods.

Findings

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

Demonstrates strong exploration capabilities

Shows good transferability of the approach

Abstract

Many score-based active learning methods have been successfully applied to graph-structured data, aiming to reduce the number of labels and achieve better performance of graph neural networks based on predefined score functions. However, these algorithms struggle to learn policy distributions that are proportional to rewards and have limited exploration capabilities. In this paper, we innovatively formulate the graph active learning problem as a generative process, named GFlowGNN, which generates various samples through sequential actions with probabilities precisely proportional to a predefined reward function. Furthermore, we propose the concept of flow nodes and flow features to efficiently model graphs as flows based on generative flow networks, where the policy network is trained with specially designed rewards. Extensive experiments on real datasets show that the proposed approach has good exploration capability and transferability, outperforming various state-of-the-art methods.