# Restricting the Flow: Information Bottlenecks for Attribution

arXiv: https://arxiv.org/abs/2001.00396 · HTML: https://mlsanity.com/paper/2001.00396/

## Key facts

- Cited by 110 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jan 2020.

## Built on by (most cited first, 30 of 110)

- [FastSHAP: Real-Time Shapley Value Estimation](https://mlsanity.com/paper/2107.07436/) (2021)
- [Acquisition of Chess Knowledge in AlphaZero](https://mlsanity.com/paper/2111.09259/) (2021)
- [BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentation](https://mlsanity.com/paper/2103.08907/) (2021)
- [Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2110.06530/) (2021)
- [Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classification](https://mlsanity.com/paper/2303.08446/) (2023)
- [Learning Bottleneck Concepts in Image Classification](https://mlsanity.com/paper/2304.10131/) (2023)
- [Improving Subgraph Recognition with Variational Graph Information Bottleneck](https://mlsanity.com/paper/2112.09899/) (2021)
- [Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution](https://mlsanity.com/paper/2312.17174/) (2023)
- [Neural Response Interpretation through the Lens of Critical Pathways](https://mlsanity.com/paper/2103.16886/) (2021)
- [Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck](https://mlsanity.com/paper/2204.02735/) (2022)
- [Towards Better Understanding Attribution Methods](https://mlsanity.com/paper/2205.10435/) (2022)
- [The Eval4NLP Shared Task on Explainable Quality Estimation: Overview and Results](https://mlsanity.com/paper/2110.04392/) (2021)
- [AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression](https://mlsanity.com/paper/2305.10010/) (2023)
- [Opti-CAM: Optimizing saliency maps for interpretability](https://mlsanity.com/paper/2301.07002/) (2023)
- [Optimal ablation for interpretability](https://mlsanity.com/paper/2409.09951/) (2024)
- [Listen to Interpret: Post-hoc Interpretability for Audio Networks with NMF](https://mlsanity.com/paper/2202.11479/) (2022)
- [Translation Error Detection as Rationale Extraction](https://mlsanity.com/paper/2108.12197/) (2021)
- [REV: Information-Theoretic Evaluation of Free-Text Rationales](https://mlsanity.com/paper/2210.04982/) (2022)
- [Do Explanations Explain? Model Knows Best](https://mlsanity.com/paper/2203.02269/) (2022)
- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information](https://mlsanity.com/paper/2110.01471/) (2021)
- [HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation](https://mlsanity.com/paper/2304.01811/) (2023)
- [Integrated Grad-CAM: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks via Integrated Gradient-Based Scoring](https://mlsanity.com/paper/2102.07805/) (2021)
- [A Game-Theoretic Taxonomy of Visual Concepts in DNNs](https://mlsanity.com/paper/2106.10938/) (2021)
- [Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration](https://mlsanity.com/paper/2103.12300/) (2021)
- [Towards Explainable Evaluation Metrics for Natural Language Generation](https://mlsanity.com/paper/2203.11131/) (2022)
- [DEAL: Disentangle and Localize Concept-level Explanations for VLMs](https://mlsanity.com/paper/2407.14412/) (2024)
- [Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group Masks](https://mlsanity.com/paper/2104.04488/) (2021)
- [RELAX: Representation Learning Explainability](https://mlsanity.com/paper/2112.10161/) (2021)
- [Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods](https://mlsanity.com/paper/2212.06872/) (2022)

## Abstract (arXiv)

Attribution methods provide insights into the decision-making of machine learning models like artificial neural networks. For a given input sample, they assign a relevance score to each individual input variable, such as the pixels of an image. In this work we adapt the information bottleneck concept for attribution. By adding noise to intermediate feature maps we restrict the flow of information and can quantify (in bits) how much information image regions provide. We compare our method against ten baselines using three different metrics on VGG-16 and ResNet-50, and find that our methods outperform all baselines in five out of six settings. The method's information-theoretic foundation provides an absolute frame of reference for attribution values (bits) and a guarantee that regions scored close to zero are not necessary for the network's decision. For reviews: https://openreview.net/forum?id=S1xWh1rYwB For code: https://github.com/BioroboticsLab/IBA