EVINET: Towards Open-World Graph Learning via Evidential Reasoning Network
Guan, Weijie, Wang, Haohui, Kang, Jian, Liu, Lihui, Zhou, Dawei
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Aug-4-2025
- Country:
- Africa > Rwanda
- Asia > Myanmar
- Tanintharyi Region > Dawei (0.05)
- Europe
- Austria > Vienna (0.14)
- France (0.04)
- Hungary > Hajdú-Bihar County
- Debrecen (0.04)
- Ireland > Leinster
- County Dublin > Dublin (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- North America
- Canada
- British Columbia > Metro Vancouver Regional District
- Vancouver (0.04)
- Ontario > Toronto (0.05)
- Quebec > Montreal (0.04)
- British Columbia > Metro Vancouver Regional District
- United States
- California
- Alameda County > Berkeley (0.04)
- Los Angeles County > Long Beach (0.04)
- San Francisco County > San Francisco (0.14)
- Hawaii > Honolulu County
- Honolulu (0.04)
- Maryland > Baltimore (0.04)
- Michigan > Wayne County
- Detroit (0.04)
- New York
- Monroe County > Rochester (0.04)
- New York County > New York City (0.04)
- Virginia > Montgomery County
- Blacksburg (0.04)
- California
- Canada
- South America > Colombia
- Meta Department > Villavicencio (0.04)
- Genre:
- Research Report > New Finding (0.46)
- Technology: