RISAN: Robust Instance Specific Abstention Network

TL;DR

This paper introduces a deep learning architecture for instance-specific abstain classifiers using a double sigmoid loss, demonstrating robustness to label noise and providing theoretical guarantees.

Contribution

It proposes a novel deep architecture with a double sigmoid loss for reject option classification, including theoretical analysis and empirical validation.

Findings

Performs comparably to state-of-the-art methods

Robust against label noise

Provides feature visualizations for abstaining decisions

Abstract

In this paper, we propose deep architectures for learning instance specific abstain (reject option) binary classifiers. The proposed approach uses double sigmoid loss function as described by Kulin Shah and Naresh Manwani in ("Online Active Learning of Reject Option Classifiers", AAAI, 2020), as a performance measure. We show that the double sigmoid loss is classification calibrated. We also show that the excess risk of 0-d-1 loss is upper bounded by the excess risk of double sigmoid loss. We derive the generalization error bounds for the proposed architecture for reject option classifiers. To show the effectiveness of the proposed approach, we experiment with several real world datasets. We observe that the proposed approach not only performs comparable to the state-of-the-art approaches, it is also robust against label noise. We also provide visualizations to observe the important features learned by the network corresponding to the abstaining decision.