Timezone: »
Thanks to graph neural networks (GNNs), semi-supervised node classification has shown the state-of-the-art performance in graph data. However, GNNs have not considered different types of uncertainties associated with class probabilities to minimize risk of increasing misclassification under uncertainty in real life. In this work, we propose a multi-source uncertainty framework using a GNN that reflects various types of predictive uncertainties in both deep learning and belief/evidence theory domains for node classification predictions. By collecting evidence from the given labels of training nodes, the Graph-based Kernel Dirichlet distribution Estimation (GKDE) method is designed for accurately predicting node-level Dirichlet distributions and detecting out-of-distribution (OOD) nodes. We validated the outperformance of our proposed model compared to the state-of-the-art counterparts in terms of misclassification detection and OOD detection based on six real network datasets. We found that dissonance-based detection yielded the best results on misclassification detection while vacuity-based detection was the best for OOD detection. To clarify the reasons behind the results, we provided the theoretical proof that explains the relationships between different types of uncertainties considered in this work.
Author Information
Xujiang Zhao (The University of Texas at Dallas)
Feng Chen (UT Dallas)
Shu Hu (University at Buffalo, State University of New York)
Jin-Hee Cho (Virginia Tech)
Related Events (a corresponding poster, oral, or spotlight)
-
2020 Poster: Uncertainty Aware Semi-Supervised Learning on Graph Data »
Thu. Dec 10th 05:00 -- 07:00 AM Room Poster Session 4 #1258
More from the Same Authors
-
2021 : A Nested Bi-level Optimization Framework for Robust Few Shot Learning »
Krishnateja Killamsetty · Changbin Li · Chen Zhao · Rishabh Iyer · Feng Chen -
2023 Poster: Improvements on Uncertainty Quantification for Node Classification via Distance Based Regularization »
Russell Hart · Linlin Yu · Yifei Lou · Feng Chen -
2021 Poster: RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning »
Krishnateja Killamsetty · Xujiang Zhao · Feng Chen · Rishabh Iyer -
2020 Poster: Multifaceted Uncertainty Estimation for Label-Efficient Deep Learning »
Weishi Shi · Xujiang Zhao · Feng Chen · Qi Yu -
2020 Poster: Learning by Minimizing the Sum of Ranked Range »
Shu Hu · Yiming Ying · xin wang · Siwei Lyu