Active Learning Framework for Incomplete Networks

Tung Khong, Cong Tran, Cuong Pham

Keywords: Active Learning, Incomplete Graphs, Graph Neural Networks, Node Classification, Link Prediction, Semi-Supervised Learning

TL;DR: an active learning approach tailored specifically for solving the node classification problem in incomplete graphs

Abstract: Significant progression has been made in active learning algorithms for graph networks in various tasks. However real-world applications frequently involve incomplete graphs with missing links, which pose the challenge that existing approaches might not adequately address. This paper presents an active learning approach tailored specifically for handling incomplete graphs, termed ALIN. Our algorithm employs graph neural networks (GNN) to generate node embeddings and calculates losses for both node classification and link prediction tasks. The losses are combined with appropriate weights and iteratively updating the GNN, ALIN efficiently queries nodes in batches, thereby achieving a balance between training feedbacks and resource utilization. Our empirical experiments have shown ALIN can surpass state-of-the-art baselines on Cora, Citeseer, Pubmed, and Coauthor-CS datasets.

List Of Authors: Khong, Tung and Tran, Cong and Pham, Cuong

Code Url: https://github.com/manhtung001/ALIN

Video Url: https://www.youtube.com/watch?v=-UHUPH_DPZ4&t=153s

Submission Number: 591