Guan, WeijieWang, HaohuiKang, JianLiu, LihuiZhou, Dawei2025-09-102025-09-102025-08-03https://hdl.handle.net/10919/137728Graph 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.application/pdfenCreative Commons Attribution 4.0 InternationalE<small>VI</small>N<small>ET</small>: Evidential Reasoning Network for Resilient Graph Learning in the Open and Noisy EnvironmentsArticle - Refereed2025-09-01The author(s)https://doi.org/10.1145/3711896.3736945