EVINET: Towards Open-World Graph Learning via Evidential Reasoning Network

TL;DR

EVINET is a novel graph learning framework that uses evidential reasoning to effectively detect misclassifications and out-of-distribution data, advancing open-world graph learning capabilities.

Contribution

The paper introduces EVINET, integrating Beta embedding with subjective logic to improve uncertainty estimation for open-world graph learning tasks.

Findings

Outperforms state-of-the-art in multiple detection metrics

Effectively detects misclassification and out-of-distribution data

Highlights importance of uncertainty estimation in graph learning

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-of-distribution 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 out-of-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.