Uday Bhaskar K supervised by Dr. Naresh Manwani  received his Master of Science in Computer Science and Engineering (CSE). Here’s a summary of his research work on Node Classification with Reject Option:

Node Classification is one of the key tasks in graph learning. While Graph Neural Networks (GNNs) have been tremendously successful in learning on graph-structured data, they are also known to be sensitive and unreliable for real deployment, and their adaptivity to reject option settings has not been previously explored. In this work, we propose NCwR, a novel approach to node classification in Graph Neural Networks with an integrated reject option. This allows the model to abstain from making predictions for samples with high uncertainty. We propose cost-based and coverage-based methods for classification with abstention. We perform experiments using our method on standard citation network datasets Cora, CiteSeer, PubMed and ogbn-arxiv. We also model the Legal judgment prediction problem on the ILDC dataset as a node classification problem, where nodes represent legal cases and edges represent citations. We further interpret the model by analysing the cases in which it abstains from predicting and visualising which part of the input features influenced this decision. 

May 2026