Saved in:
Bibliographic Details
Main Authors: Arrighi, Leonardo, Belloni, Julia Eva, Gallet, Aurélie, Gentile, Ivan, Lippi, Matteo, Zullich, Marco
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.22540
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908991080103936
author Arrighi, Leonardo
Belloni, Julia Eva
Gallet, Aurélie
Gentile, Ivan
Lippi, Matteo
Zullich, Marco
author_facet Arrighi, Leonardo
Belloni, Julia Eva
Gallet, Aurélie
Gentile, Ivan
Lippi, Matteo
Zullich, Marco
contents Most Neural Networks (NNs) for classification are trained using Cross-Entropy as a loss function. This approach requires the model to have an explicit classification layer. However, there exist alternative approaches, such as Contrastive Learning (CL). Instead of explicitly operating a classification, CL has the NN produce an embedding space where projections of similar data are pulled together, while projections of dissimilar data are pushed apart. In the case of Supervised CL (SCL), labels are adopted as similarity criteria, thus creating an embedding space where the projected data points are well-clustered. SCL provides crucial advantages over CE with regard to adversarial robustness and out-of-distribution detection, thus making it a more natural choice in safety-critical scenarios. In the present paper, we empirically show that NNs for image classification trained with SCL present higher-quality feature attribution explanations than CL with regard to faithfulness, complexity, and continuity. These results reinforce previous findings about CL-based approaches when targeting more trustworthy and transparent NNs and can guide practitioners in the selection of training objectives targeting not only accuracy, but also transparency of the models.
format Preprint
id arxiv_https___arxiv_org_abs_2604_22540
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle On the Properties of Feature Attribution for Supervised Contrastive Learning
Arrighi, Leonardo
Belloni, Julia Eva
Gallet, Aurélie
Gentile, Ivan
Lippi, Matteo
Zullich, Marco
Machine Learning
Artificial Intelligence
Most Neural Networks (NNs) for classification are trained using Cross-Entropy as a loss function. This approach requires the model to have an explicit classification layer. However, there exist alternative approaches, such as Contrastive Learning (CL). Instead of explicitly operating a classification, CL has the NN produce an embedding space where projections of similar data are pulled together, while projections of dissimilar data are pushed apart. In the case of Supervised CL (SCL), labels are adopted as similarity criteria, thus creating an embedding space where the projected data points are well-clustered. SCL provides crucial advantages over CE with regard to adversarial robustness and out-of-distribution detection, thus making it a more natural choice in safety-critical scenarios. In the present paper, we empirically show that NNs for image classification trained with SCL present higher-quality feature attribution explanations than CL with regard to faithfulness, complexity, and continuity. These results reinforce previous findings about CL-based approaches when targeting more trustworthy and transparent NNs and can guide practitioners in the selection of training objectives targeting not only accuracy, but also transparency of the models.
title On the Properties of Feature Attribution for Supervised Contrastive Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2604.22540