Active Learning Framework for Incomplete Networks

Tung Khong, Cong Tran, Cuong Pham
Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence, PMLR 244:1981-1998, 2024.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v244-khong24a, title = {Active Learning Framework for Incomplete Networks}, author = {Khong, Tung and Tran, Cong and Pham, Cuong}, booktitle = {Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence}, pages = {1981--1998}, year = {2024}, editor = {Kiyavash, Negar and Mooij, Joris M.}, volume = {244}, series = {Proceedings of Machine Learning Research}, month = {15--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v244/main/assets/khong24a/khong24a.pdf}, url = {https://proceedings.mlr.press/v244/khong24a.html}, 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.} }
Endnote
%0 Conference Paper %T Active Learning Framework for Incomplete Networks %A Tung Khong %A Cong Tran %A Cuong Pham %B Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2024 %E Negar Kiyavash %E Joris M. Mooij %F pmlr-v244-khong24a %I PMLR %P 1981--1998 %U https://proceedings.mlr.press/v244/khong24a.html %V 244 %X 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.
APA
Khong, T., Tran, C. & Pham, C.. (2024). Active Learning Framework for Incomplete Networks. Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 244:1981-1998 Available from https://proceedings.mlr.press/v244/khong24a.html.

Related Material