Active Learning for Graph Embedding

Abstract

Graph embedding provides an efficient solution for graph analysis by converting the graph into a low-dimensional space which preserves the structure information. In contrast to the graph structure data, the i.i.d. node embedding can be processed efficiently in terms of both time and space. Current semi-supervised graph embedding algorithms assume the labelled nodes are given, which may not be always true in the real world. While manually label all training data is inapplicable, how to select the subset of training data to label so as to maximize the graph analysis task performance is of great importance. This motivates our proposed active graph embedding (AGE) framework, in which we design a general active learning query strategy for any semi-supervised graph embedding algorithm. AGE selects the most informative nodes as the training labelled nodes based on the graphical information (i.e., node centrality) as well as the learnt node embedding (i.e., node classification uncertainty and node embedding representativeness). Different query criteria are combined with the time-sensitive parameters which shift the focus from graph based query criteria to embedding based criteria as the learning progresses. Experiments have been conducted on three public data sets and the results verified the effectiveness of each component of our query strategy and the power of combining them using time-sensitive parameters. Our code is available online at: https://github.com/vwz/AGE.

Technical Report

References in corpus (1)

• Grammar-Based Random Walkers in Semantic Networks

Cited by in corpus (15)

• Graph Neural Networks: A Review of Methods and Applications
• SEAL: Semi-supervised Adversarial Active Learning on Attributed Graphs
• Graph Neural Networks: Methods, Applications, and Opportunities
• Active Learning for Graph Neural Networks via Node Feature Propagation
• Graph Policy Network for Transferable Active Learning on Graphs
• JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks
• Adversarial Model Extraction on Graph Neural Networks
• ActiveHNE: Active Heterogeneous Network Embedding
• Sequential Graph Convolutional Network for Active Learning
• Regional based query in graph active learning
• Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks
• When Contrastive Learning Meets Active Learning: A Novel Graph Active Learning Paradigm with Self-Supervision
• ALPINE: Active Link Prediction using Network Embedding
• Meta-Active Learning for Node Response Prediction in Graphs
• MetAL: Active Semi-Supervised Learning on Graphs via Meta Learning