Pith. sign in

REVIEW 2 cited by

C-SENN: Contrastive Self-Explaining Neural Network

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.09575 v2 pith:OT3GCGJZ submitted 2022-06-20 cs.CV cs.AIcs.LG

classification cs.CVcs.AIcs.LG
keywords conceptscontrastivelearningnetworkneuralself-explainingc-sennconcept
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this study, we use a self-explaining neural network (SENN), which learns unsupervised concepts, to acquire concepts that are easy for people to understand automatically. In concept learning, the hidden layer retains verbalizable features relevant to the output, which is crucial when adapting to real-world environments where explanations are required. However, it is known that the interpretability of concepts output by SENN is reduced in general settings, such as autonomous driving scenarios. Thus, this study combines contrastive learning with concept learning to improve the readability of concepts and the accuracy of tasks. We call this model Contrastive Self-Explaining Neural Network (C-SENN).

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Self-Explaining Reinforcement Learning for Mobile Network Resource Allocation

    cs.LG 2025-09 conditional novelty 5.0 of 10

    A self-explaining neural network policy trained with PPO matches deep RL performance on mobile network resource allocation while generating local and aggregate global explanations, though the explanation-quality claim...

  2. A Comprehensive Survey on the Risks and Limitations of Concept-based Models

    cs.LG 2025-05 conditional novelty 4.0 of 10

    A survey cataloging the main vulnerabilities of supervised and unsupervised concept-based models, including concept leakage, spurious correlations, and intervention failures.

Pith tools