# Explaining a black-box using Deep Variational Information Bottleneck Approach

arXiv: https://arxiv.org/abs/1902.06918 · HTML: https://mlsanity.com/paper/1902.06918/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2019.

## Built on by (most cited first, 30 of 36)

- [The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations](https://mlsanity.com/paper/2106.00786/) (2021)
- [Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations](https://mlsanity.com/paper/2210.11584/) (2022)
- [Reinforced Causal Explainer for Graph Neural Networks](https://mlsanity.com/paper/2204.11028/) (2022)
- [Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF](https://mlsanity.com/paper/2202.11479/) (2022)
- [Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility](https://mlsanity.com/paper/2207.04895/) (2022)
- [Cauchy-Schwarz Divergence Information Bottleneck for Regression](https://mlsanity.com/paper/2404.17951/) (2024)
- [R2-Trans:Fine-Grained Visual Categorization with Redundancy Reduction](https://mlsanity.com/paper/2204.10095/) (2022)
- [Interpretability with full complexity by constraining feature information](https://mlsanity.com/paper/2211.17264/) (2022)
- [Posthoc Interpretation via Quantization](https://mlsanity.com/paper/2303.12659/) (2023)
- [Improving Interpretability via Explicit Word Interaction Graph Layer](https://mlsanity.com/paper/2302.02016/) (2023)
- [Hierarchical Interpretation of Neural Text Classification](https://mlsanity.com/paper/2202.09792/) (2022)
- [Tackling Interpretability in Audio Classification Networks with Non-negative Matrix Factorization](https://mlsanity.com/paper/2305.07132/) (2023)
- [DocVXQA: Context-Aware Visual Explanations for Document Question Answering](https://mlsanity.com/paper/2505.07496/) (2025)
- [Concept-Centric Token Interpretation for Vector-Quantized Generative Models](https://mlsanity.com/paper/2506.00698/) (2025)
- [Variational Distillation for Multi-View Learning](https://mlsanity.com/paper/2206.09548/) (2022)
- [An Additive Instance-Wise Approach to Multi-class Model Interpretation](https://mlsanity.com/paper/2207.03113/) (2022)
- [An Information Bottleneck Characterization of the Understanding-Workload Tradeoff](https://mlsanity.com/paper/2310.07802/) (2023)
- [CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning](https://mlsanity.com/paper/2503.00062/) (2025)
- [Revisiting Attention Weights as Explanations from an Information Theoretic Perspective](https://mlsanity.com/paper/2211.07714/) (2022)
- [Infor-Coef: Information Bottleneck-based Dynamic Token Downsampling for Compact and Efficient language model](https://mlsanity.com/paper/2305.12458/) (2023)
- [Exploring Heterogeneity and Uncertainty for Graph-based Cognitive Diagnosis Models in Intelligent Education](https://mlsanity.com/paper/2403.05559/) (2024)
- [InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory](https://mlsanity.com/paper/2505.19820/) (2025)
- [Deep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognition](https://mlsanity.com/paper/2404.02696/) (2024)
- [Task-Augmented Cross-View Imputation Network for Partial Multi-View Incomplete Multi-Label Classification](https://mlsanity.com/paper/2409.07931/) (2024)
- [BlindU: Blind Machine Unlearning without Revealing Erasing Data](https://mlsanity.com/paper/2601.07214/) (2026)
- [Training deep physical neural networks with local physical information bottleneck](https://mlsanity.com/paper/2602.09569/) (2026)
- [Progressive Interpretation Synthesis: Interpreting Task Solving by Quantifying Previously Used and Unused Information](https://mlsanity.com/paper/2101.02879/) (2021)
- [Reinforcement Explanation Learning](https://mlsanity.com/paper/2111.13406/) (2021)
- [Explanation-based Counterfactual Retraining(XCR): A Calibration Method for Black-box Models](https://mlsanity.com/paper/2206.11126/) (2022)
- [BELLA: Black box model Explanations by Local Linear Approximations](https://mlsanity.com/paper/2305.11311/) (2023)

## Abstract (arXiv)

Interpretable machine learning has gained much attention recently. Briefness and comprehensiveness are necessary in order to provide a large amount of information concisely when explaining a black-box decision system. However, existing interpretable machine learning methods fail to consider briefness and comprehensiveness simultaneously, leading to redundant explanations. We propose the variational information bottleneck for interpretation, VIBI, a system-agnostic interpretable method that provides a brief but comprehensive explanation. VIBI adopts an information theoretic principle, information bottleneck principle, as a criterion for finding such explanations. For each instance, VIBI selects key features that are maximally compressed about an input (briefness), and informative about a decision made by a black-box system on that input (comprehensive). We evaluate VIBI on three datasets and compare with state-of-the-art interpretable machine learning methods in terms of both interpretability and fidelity evaluated by human and quantitative metrics