# DISSECT: Disentangled Simultaneous Explanations via Concept Traversals

arXiv: https://arxiv.org/abs/2105.15164 · HTML: https://mlsanity.com/paper/2105.15164/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 59 of its 90 references that are in the map.
- First posted on arXiv 31 May 2021.

## Builds on (most cited first, 30 of 59)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://mlsanity.com/paper/1802.07623/) (2018)

## Built on by (most cited first, 30 of 37)

- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [Getting aligned on representational alignment](https://mlsanity.com/paper/2310.13018/) (2023)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods](https://mlsanity.com/paper/2111.02398/) (2021)
- [Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero](https://mlsanity.com/paper/2310.16410/) (2023)
- [Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision](https://mlsanity.com/paper/2303.00885/) (2023)
- [Xplique: A Deep Learning Explainability Toolbox](https://mlsanity.com/paper/2206.04394/) (2022)
- [Human-Centered Concept Explanations for Neural Networks](https://mlsanity.com/paper/2202.12451/) (2022)
- [Concept Gradient: Concept-based Interpretation Without Linear Assumption](https://mlsanity.com/paper/2208.14966/) (2022)
- [Neural Concept Binder](https://mlsanity.com/paper/2406.09949/) (2024)
- [Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases](https://mlsanity.com/paper/2212.02648/) (2022)
- [Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement](https://mlsanity.com/paper/2311.15303/) (2023)
- [Evaluating Readability and Faithfulness of Concept-based Explanations](https://mlsanity.com/paper/2404.18533/) (2024)
- [Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks](https://mlsanity.com/paper/2304.05727/) (2023)
- [A survey on Concept-based Approaches For Model Improvement](https://mlsanity.com/paper/2403.14566/) (2024)
- [Generating Counterfactual Trajectories with Latent Diffusion Models for Concept Discovery](https://mlsanity.com/paper/2404.10356/) (2024)
- [ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation [Technical Report]](https://mlsanity.com/paper/2311.15438/) (2023)
- [Counterfactual Concept Bottleneck Models](https://mlsanity.com/paper/2402.01408/) (2024)
- [DisCoM-KD: Cross-Modal Knowledge Distillation via Disentanglement Representation and Adversarial Learning](https://mlsanity.com/paper/2408.07080/) (2024)
- [Identifying the Context Shift between Test Benchmarks and Production Data](https://mlsanity.com/paper/2207.01059/) (2022)
- [Benchmarking and Enhancing Disentanglement in Concept-Residual Models](https://mlsanity.com/paper/2312.00192/) (2023)
- [The Gaussian Discriminant Variational Autoencoder (GdVAE): A Self-Explainable Model with Counterfactual Explanations](https://mlsanity.com/paper/2409.12952/) (2024)
- [Img2Tab: Automatic Class Relevant Concept Discovery from StyleGAN Features for Explainable Image Classification](https://mlsanity.com/paper/2301.06324/) (2023)
- [Beyond Rewards: a Hierarchical Perspective on Offline Multiagent Behavioral Analysis](https://mlsanity.com/paper/2206.09046/) (2022)
- [Hierarchical Symbolic Reasoning in Hyperbolic Space for Deep Discriminative Models](https://mlsanity.com/paper/2207.01916/) (2022)
- [Learning Unsupervised Hierarchies of Audio Concepts](https://mlsanity.com/paper/2207.11231/) (2022)
- [Reimagining Anomalies: What If Anomalies Were Normal?](https://mlsanity.com/paper/2402.14469/) (2024)
- [Restyling Unsupervised Concept Based Interpretable Networks with Generative Models](https://mlsanity.com/paper/2407.01331/) (2024)
- [A Survey on Interpretability in Visual Recognition](https://mlsanity.com/paper/2507.11099/) (2025)

## Abstract (arXiv)

Explaining deep learning model inferences is a promising venue for scientific understanding, improving safety, uncovering hidden biases, evaluating fairness, and beyond, as argued by many scholars. One of the principal benefits of counterfactual explanations is allowing users to explore "what-if" scenarios through what does not and cannot exist in the data, a quality that many other forms of explanation such as heatmaps and influence functions are inherently incapable of doing. However, most previous work on generative explainability cannot disentangle important concepts effectively, produces unrealistic examples, or fails to retain relevant information. We propose a novel approach, DISSECT, that jointly trains a generator, a discriminator, and a concept disentangler to overcome such challenges using little supervision. DISSECT generates Concept Traversals (CTs), defined as a sequence of generated examples with increasing degrees of concepts that influence a classifier's decision. By training a generative model from a classifier's signal, DISSECT offers a way to discover a classifier's inherent "notion" of distinct concepts automatically rather than rely on user-predefined concepts. We show that DISSECT produces CTs that (1) disentangle several concepts, (2) are influential to a classifier's decision and are coupled to its reasoning due to joint training (3), are realistic, (4) preserve relevant information, and (5) are stable across similar inputs. We validate DISSECT on several challenging synthetic and realistic datasets where previous methods fall short of satisfying desirable criteria for interpretability and show that it performs consistently well and better than existing methods. Finally, we present experiments showing applications of DISSECT for detecting potential biases of a classifier and identifying spurious artifacts that impact predictions.