Node Classification With Integrated Reject Option

TL;DR

This paper introduces NCwR, a novel GNN-based node classification method with an integrated reject option, enabling the model to abstain from uncertain predictions, improving interpretability and robustness.

Contribution

It proposes a new approach for node classification with abstention in GNNs, including cost-based and coverage-based methods, and demonstrates its effectiveness on multiple datasets.

Findings

Improved accuracy with abstention on citation datasets

Effective modeling of legal judgment prediction as node classification

Enhanced interpretability through feature visualization

Abstract

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.