# Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approaches

arXiv: https://arxiv.org/abs/2104.06917 · HTML: https://mlsanity.com/paper/2104.06917/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 14 Apr 2021.

## Builds on (most cited first, 9 of 9)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [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 Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Weakly-Supervised Disentanglement Without Compromises](https://mlsanity.com/paper/2002.02886/) (2020)
- [Concept Whitening for Interpretable Image Recognition](https://mlsanity.com/paper/2002.01650/) (2020)
- [Flexibly Fair Representation Learning by Disentanglement](https://mlsanity.com/paper/1906.02589/) (2019)
- [Now You See Me (CME): Concept-based Model Extraction](https://mlsanity.com/paper/2010.13233/) (2020)

## Built on by (most cited first, 17 of 17)

- [GlanceNets: Interpretabile, Leak-proof Concept-based Models](https://mlsanity.com/paper/2205.15612/) (2022)
- [GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks](https://mlsanity.com/paper/2107.11889/) (2021)
- [Towards Robust Metrics for Concept Representation Evaluation](https://mlsanity.com/paper/2301.10367/) (2023)
- [Concept Embedding Analysis: A Review](https://mlsanity.com/paper/2203.13909/) (2022)
- [Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?](https://mlsanity.com/paper/2409.13456/) (2024)
- [If Concept Bottlenecks are the Question, are Foundation Models the Answer?](https://mlsanity.com/paper/2504.19774/) (2025)
- [When are Post-hoc Conceptual Explanations Identifiable?](https://mlsanity.com/paper/2206.13872/) (2022)
- [Leakage and Interpretability in Concept-Based Models](https://mlsanity.com/paper/2504.14094/) (2025)
- [Algorithmic Concept-based Explainable Reasoning](https://mlsanity.com/paper/2107.07493/) (2021)
- [Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability](https://mlsanity.com/paper/2304.14864/) (2023)
- [A survey on Concept-based Approaches For Model Improvement](https://mlsanity.com/paper/2403.14566/) (2024)
- [Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddings](https://mlsanity.com/paper/2201.00572/) (2022)
- [Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces](https://mlsanity.com/paper/2311.14435/) (2023)
- [Can we Constrain Concept Bottleneck Models to Learn Semantically Meaningful Input Features?](https://mlsanity.com/paper/2402.00912/) (2024)
- [Learning Concept-Based Causal Transition and Symbolic Reasoning for Visual Planning](https://mlsanity.com/paper/2310.03325/) (2023)
- [Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations](https://mlsanity.com/paper/2605.16405/) (2026)
- [DeCoDe: Defer-and-Complement Decision-Making via Decoupled Concept Bottleneck Models](https://mlsanity.com/paper/2505.19220/) (2025)

## Abstract (arXiv)

Concept-based explanations have emerged as a popular way of extracting human-interpretable representations from deep discriminative models. At the same time, the disentanglement learning literature has focused on extracting similar representations in an unsupervised or weakly-supervised way, using deep generative models. Despite the overlapping goals and potential synergies, to our knowledge, there has not yet been a systematic comparison of the limitations and trade-offs between concept-based explanations and disentanglement approaches. In this paper, we give an overview of these fields, comparing and contrasting their properties and behaviours on a diverse set of tasks, and highlighting their potential strengths and limitations. In particular, we demonstrate that state-of-the-art approaches from both classes can be data inefficient, sensitive to the specific nature of the classification/regression task, or sensitive to the employed concept representation.