RISAN: Robust Instance Specific Abstention Network
This work addresses the need for robust abstention mechanisms in classification, particularly for noisy data, but it is incremental as it builds on existing loss functions and architectures.
The paper tackles the problem of learning instance-specific abstention in binary classifiers by proposing a deep architecture using a double sigmoid loss, showing it is classification calibrated and provides generalization error bounds. The approach performs comparably to state-of-the-art methods on real-world datasets and demonstrates robustness against label noise.
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.