Neural networks trained via supervised contrastive learning yield feature attributions that are more faithful, less complex, and more continuous than those from cross-entropy trained networks.
In: The Thirteenth International Conference on Learning Representations (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A cosine-similarity metric on SHAP feature attributions is proposed to quantify explanation stability for same-label inputs under perturbations in transformer-based sentiment classifiers.
citing papers explorer
-
On the Properties of Feature Attribution for Supervised Contrastive Learning
Neural networks trained via supervised contrastive learning yield feature attributions that are more faithful, less complex, and more continuous than those from cross-entropy trained networks.
-
Empirical Characterization of Rationale Stability Under Controlled Perturbations for Explainable Pattern Recognition
A cosine-similarity metric on SHAP feature attributions is proposed to quantify explanation stability for same-label inputs under perturbations in transformer-based sentiment classifiers.