Meta-Active Learning for Node Response Prediction in Graphs

TL;DR

This paper introduces a novel active learning approach combined with meta-learning for node response prediction in attributed graphs, effectively selecting nodes to improve prediction with minimal observations, especially in unbalanced data scenarios.

Contribution

It proposes a graph convolutional neural network-based active meta-learning method for node response prediction, capable of handling unseen response variables and optimizing node selection via reinforcement learning.

Findings

Effective in 11 road congestion prediction tasks

Improves prediction accuracy with fewer observed nodes

Handles unseen response variables in graphs

Abstract

Meta-learning is an important approach to improve machine learning performance with a limited number of observations for target tasks. However, when observations are unbalancedly obtained, it is difficult to improve the performance even with meta-learning methods. In this paper, we propose an active learning method for meta-learning on node response prediction tasks in attributed graphs, where nodes to observe are selected to improve performance with as few observed nodes as possible. With the proposed method, we use models based on graph convolutional neural networks for both predicting node responses and selecting nodes, by which we can predict responses and select nodes even for graphs with unseen response variables. The response prediction model is trained by minimizing the expected test error. The node selection model is trained by maximizing the expected error reduction with reinforcement learning. We demonstrate the effectiveness of the proposed method with 11 types of road congestion prediction tasks.