# Benchmarking and Enhancing Disentanglement in Concept-Residual Models

arXiv: https://arxiv.org/abs/2312.00192 · HTML: https://mlsanity.com/paper/2312.00192/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 30 Nov 2023.

## Builds on (most cited first, 24 of 24)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [Concept Whitening for Interpretable Image Recognition](https://mlsanity.com/paper/2002.01650/) (2020)
- [Promises and Pitfalls of Black-Box Concept Learning Models](https://mlsanity.com/paper/2106.13314/) (2021)
- [Acquisition of Chess Knowledge in AlphaZero](https://mlsanity.com/paper/2111.09259/) (2021)
- [Do Concept Bottleneck Models Learn as Intended?](https://mlsanity.com/paper/2105.04289/) (2021)
- [Probabilistic Concept Bottleneck Models](https://mlsanity.com/paper/2306.01574/) (2023)
- [Iterative Normalization: Beyond Standardization towards Efficient Whitening](https://mlsanity.com/paper/1904.03441/) (2019)
- [Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods](https://mlsanity.com/paper/2111.02398/) (2021)
- [Concept Bottleneck Model with Additional Unsupervised Concepts](https://mlsanity.com/paper/2202.01459/) (2022)
- [Interactive Concept Bottleneck Models](https://mlsanity.com/paper/2212.07430/) (2022)
- [A Closer Look at the Intervention Procedure of Concept Bottleneck Models](https://mlsanity.com/paper/2302.14260/) (2023)
- [Visual Concept-Metaconcept Learning](https://mlsanity.com/paper/2002.01464/) (2020)
- [On Interpretability of Deep Learning based Skin Lesion Classifiers using Concept Activation Vectors](https://mlsanity.com/paper/2005.02000/) (2020)
- [DISSECT: Disentangled Simultaneous Explanations via Concept Traversals](https://mlsanity.com/paper/2105.15164/) (2021)
- [Debiasing Concept-based Explanations with Causal Analysis](https://mlsanity.com/paper/2007.11500/) (2020)
- [Concept Learning for Interpretable Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2302.12232/) (2023)
- [Theory of Mind as Intrinsic Motivation for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2307.01158/) (2023)
- [Early Visual Concept Learning with Unsupervised Deep Learning](https://mlsanity.com/paper/1606.05579/) (2016)
- [Learning like a Child: Fast Novel Visual Concept Learning from Sentence Descriptions of Images](https://mlsanity.com/paper/1504.06692/) (2015)

## Built on by (most cited first, 5 of 5)

- [DCBM: Data-Efficient Visual Concept Bottleneck Models](https://mlsanity.com/paper/2412.11576/) (2024)
- [Tree-Based Leakage Inspection and Control in Concept Bottleneck Models](https://mlsanity.com/paper/2410.06352/) (2024)
- [A Comprehensive Survey on the Risks and Limitations of Concept-based Models](https://mlsanity.com/paper/2506.04237/) (2025)
- [Towards Reasonable Concept Bottleneck Models](https://mlsanity.com/paper/2506.05014/) (2025)
- [Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models](https://mlsanity.com/paper/2510.05670/) (2025)

## Abstract (arXiv)

Concept bottleneck models (CBMs) are interpretable models that first predict a set of semantically meaningful features, i.e., concepts, from observations that are subsequently used to condition a downstream task. However, the model's performance strongly depends on the engineered features and can severely suffer from incomplete sets of concepts. Prior works have proposed a side channel -- a residual -- that allows for unconstrained information flow to the downstream task, thus improving model performance but simultaneously introducing information leakage, which is undesirable for interpretability. This work proposes three novel approaches to mitigate information leakage by disentangling concepts and residuals, investigating the critical balance between model performance and interpretability. Through extensive empirical analysis on the CUB, OAI, and CIFAR 100 datasets, we assess the performance of each disentanglement method and provide insights into when they work best. Further, we show how each method impacts the ability to intervene over the concepts and their subsequent impact on task performance.