<ul><li>EviNet is a new framework introduced for graph learning in open and noisy environments.</li><li>It addresses challenges of misclassification detection and out-of-distribution detection by integrating Beta embedding within a subjective logic framework.</li><li>EviNet outperforms state-of-the-art methods in in-distribution classification, misclassification detection, and out-of-distribution detection tasks.</li><li>The framework highlights the importance of uncertainty estimation and logical reasoning for effective graph learning in open-world scenarios.</li></ul>

EviNet: Evidential Reasoning Network for Resilient Graph Learning in the Open and Noisy Environments

Discover more