Meta-Active Learning for Node Response Prediction 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.

References in corpus (14)

• Semi-Supervised Classification with Graph Convolutional Networks
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Few-Shot Learning with Graph Neural Networks
• Scaling laws in the spatial structure of urban road networks
• A Model of a Trust-based Recommendation System on a Social Network
• Hierarchically Structured Meta-learning
• Active One-shot Learning
• Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning
• Learning Algorithms for Active Learning
• Active Learning for Graph Embedding
• Dropout-based Active Learning for Regression
• Meta-Graph: Few Shot Link Prediction via Meta Learning
• The Variational Homoencoder: Learning to learn high capacity generative models from few examples
• Meta Learning with Relational Information for Short Sequences