EVINET: Evidential Reasoning Network for Resilient Graph Learning in the Open and Noisy Environments
dc.contributor.author | Guan, Weijie | en |
dc.contributor.author | Wang, Haohui | en |
dc.contributor.author | Kang, Jian | en |
dc.contributor.author | Liu, Lihui | en |
dc.contributor.author | Zhou, Dawei | en |
dc.date.accessioned | 2025-09-10T12:23:51Z | en |
dc.date.available | 2025-09-10T12:23:51Z | en |
dc.date.issued | 2025-08-03 | en |
dc.date.updated | 2025-09-01T07:47:51Z | en |
dc.description.abstract | Graph learning has been crucial to many real-world tasks, but they are often studied with a closed-world assumption, with all possible labels of data known a priori. To enable effective graph learning in an open and noisy environment, it is critical to inform the model users when the model makes a wrong prediction to in-distribution data of a known class, i.e., misclassification detection or when the model encounters out-of-distribution from novel classes, i.e., out-ofdistribution detection. This paper introduces Evidential Reasoning Network (EviNet), a framework that addresses these two challenges by integrating Beta embedding within a subjective logic framework. EviNet includes two key modules: Dissonance Reasoning for misclassification detection and Vacuity Reasoning for outof- distribution detection. Extensive experiments demonstrate that EviNet outperforms state-of-the-art methods across multiple metrics in the tasks of in-distribution classification, misclassification detection, and out-of-distribution detection. EviNet demonstrates the necessity of uncertainty estimation and logical reasoning for misclassification detection and out-of-distribution detection and paves the way for open-world graph learning. Our code and data are available at https://github.com/SSSKJ/EviNET. | en |
dc.description.version | Published version | en |
dc.format.mimetype | application/pdf | en |
dc.identifier.doi | https://doi.org/10.1145/3711896.3736945 | en |
dc.identifier.uri | https://hdl.handle.net/10919/137728 | en |
dc.language.iso | en | en |
dc.publisher | ACM | en |
dc.rights | Creative Commons Attribution 4.0 International | en |
dc.rights.holder | The author(s) | en |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | en |
dc.title | E<small>VI</small>N<small>ET</small>: Evidential Reasoning Network for Resilient Graph Learning in the Open and Noisy Environments | en |
dc.type | Article - Refereed | en |
dc.type.dcmitype | Text | en |