MetAL: Active Semi-Supervised Learning on Graphs via Meta Learning

Abstract

The objective of active learning (AL) is to train classification models with less number of labeled instances by selecting only the most informative instances for labeling. The AL algorithms designed for other data types such as images and text do not perform well on graph-structured data. Although a few heuristics-based AL algorithms have been proposed for graphs, a principled approach is lacking. In this paper, we propose MetAL, an AL approach that selects unlabeled instances that directly improve the future performance of a classification model. For a semi-supervised learning problem, we formulate the AL task as a bilevel optimization problem. Based on recent work in meta-learning, we use the meta-gradients to approximate the impact of retraining the model with any unlabeled instance on the model performance. Using multiple graph datasets belonging to different domains, we demonstrate that MetAL efficiently outperforms existing state-of-the-art AL algorithms.

arXiv comment16 pages, 4 figures

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Understanding Black-box Predictions via Influence Functions
• Simplifying Graph Convolutional Networks
• Bayesian Active Learning for Classification and Preference Learning
• Gated Graph Sequence Neural Networks
• Adversarial Attacks on Graph Neural Networks via Meta Learning
• Active One-shot Learning
• Learning Algorithms for Active Learning
• Active Learning for Graph Embedding