Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
7-2022
Abstract
Out-Of-Distribution (OOD) samples are prevalent in real-world applications. The OOD issue becomes even more severe on graph data, as the effect of OOD nodes can be potentially amplified by propagation through the graph topology. Recent works have considered the OOD detection problem, which is critical for reducing the uncertainty in learning and improving the robustness. However, no prior work considers simultaneously OOD detection and node classification on graphs in an end-to-end manner. In this paper, we study a novel problem of end-to-end open-set semisupervised node classification (OSSNC) on graphs, which deals with node classification in the presence of OOD nodes. Given the lack of supervision on OOD nodes, we introduce a latent variable to indicate in-distribution or OOD nodes in a variational inference framework, and further propose a novel algorithm named as Learning to Mix Neighbors (LMN) which learns to dampen the influence of OOD nodes through the messaging-passing in typical graph neural networks. Extensive experiments on various datasets show that the proposed method outperforms state-of-the-art baselines in terms of both node classification and OOD detection.
Keywords
Data Mining: Mining Graphs, Machine Learning: Semi-Supervised Learning
Discipline
Databases and Information Systems | Graphics and Human Computer Interfaces
Research Areas
Data Science and Engineering
Publication
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, Vienna, Austria, 2022 July 23-29
First Page
2087
Last Page
2093
Identifier
10.24963/ijcai.2022/290
Publisher
IJCAI
City or Country
Vienna, Austria
Citation
HUANG, Tiancheng; WANG, Donglin; and FANG, Yuan.
End-to-end open-set semi-supervised node classification with out-of-distribution detection. (2022). Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, Vienna, Austria, 2022 July 23-29. 2087-2093.
Available at: https://ink.library.smu.edu.sg/sis_research/7479
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
http://doi.org/10.24963/ijcai.2022/290
Included in
Databases and Information Systems Commons, Graphics and Human Computer Interfaces Commons