Node Classification With Integrated Reject Option
This work addresses the problem of uncertainty handling in node classification for graph learning applications, representing an incremental advance by adapting reject options to GNNs.
The paper tackles node classification in graph neural networks by introducing an integrated reject option that allows abstention when uncertainty is high, achieving results on citation networks and a legal judgment dataset with methods for cost-based and coverage-based abstention.
One of the key tasks in graph learning is node classification. While Graph neural networks have been used for various applications, their adaptivity to reject option setting is not previously explored. In this paper, we propose NCwR, a novel approach to node classification in Graph Neural Networks (GNNs) with an integrated reject option, which allows the model to abstain from making predictions when uncertainty is high. We propose both cost-based and coverage-based methods for classification with abstention in node classification setting using GNNs. We perform experiments using our method on three standard citation network datasets Cora, Citeseer and Pubmed and compare with relevant baselines. We also model the Legal judgment prediction problem on ILDC dataset as a node classification problem where nodes represent legal cases and edges represent citations. We further interpret the model by analyzing the cases that the model abstains from predicting by visualizing which part of the input features influenced this decision.