# Influence-Directed Explanations for Deep Convolutional Networks

arXiv: https://arxiv.org/abs/1802.03788 · HTML: https://mlsanity.com/paper/1802.03788/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2018.

## Built on by (most cited first, 30 of 31)

- [Stochastic Concept Bottleneck Models](https://mlsanity.com/paper/2406.19272/) (2024)
- [Consistent Counterfactuals for Deep Models](https://mlsanity.com/paper/2110.03109/) (2021)
- [Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?](https://mlsanity.com/paper/2401.13544/) (2024)
- [Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution](https://mlsanity.com/paper/2108.01070/) (2021)
- [Optimal ablation for interpretability](https://mlsanity.com/paper/2409.09951/) (2024)
- [Selective Ensembles for Consistent Predictions](https://mlsanity.com/paper/2111.08230/) (2021)
- [Robust Models Are More Interpretable Because Attributions Look Normal](https://mlsanity.com/paper/2103.11257/) (2021)
- [Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration](https://mlsanity.com/paper/2409.19403/) (2024)
- [Decomposing and Editing Predictions by Modeling Model Computation](https://mlsanity.com/paper/2404.11534/) (2024)
- [The Manifold Hypothesis for Gradient-Based Explanations](https://mlsanity.com/paper/2206.07387/) (2022)
- [MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Dataset](https://mlsanity.com/paper/2102.06761/) (2021)
- [Debiasing Deep Chest X-Ray Classifiers using Intra- and Post-processing Methods](https://mlsanity.com/paper/2208.00781/) (2022)
- [Classification-Regression for Chart Comprehension](https://mlsanity.com/paper/2111.14792/) (2021)
- [RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Model](https://mlsanity.com/paper/2206.00700/) (2022)
- [Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting](https://mlsanity.com/paper/2306.05093/) (2023)
- [Measuring Leakage in Concept-Based Methods: An Information Theoretic Approach](https://mlsanity.com/paper/2504.09459/) (2025)
- [Tree-Based Leakage Inspection and Control in Concept Bottleneck Models](https://mlsanity.com/paper/2410.06352/) (2024)
- [On the Robustness of Explanations of Deep Neural Network Models: A Survey](https://mlsanity.com/paper/2211.04780/) (2022)
- [Generalizing Backpropagation for Gradient-Based Interpretability](https://mlsanity.com/paper/2307.03056/) (2023)
- [TorchEsegeta: Framework for Interpretability and Explainability of Image-based Deep Learning Models](https://mlsanity.com/paper/2110.08429/) (2021)
- [Rationalizing Predictions by Adversarial Information Calibration](https://mlsanity.com/paper/2301.06009/) (2023)
- [FedDefender: Backdoor Attack Defense in Federated Learning](https://mlsanity.com/paper/2307.08672/) (2023)
- [Validating Mechanistic Interpretations: An Axiomatic Approach](https://mlsanity.com/paper/2407.13594/) (2024)
- [Faithful Explanations for Deep Graph Models](https://mlsanity.com/paper/2205.11850/) (2022)
- [RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration](https://mlsanity.com/paper/2509.12039/) (2025)
- [ExplainFix: Explainable Spatially Fixed Deep Networks](https://mlsanity.com/paper/2303.10408/) (2023)
- [DXAI: Explaining Classification by Image Decomposition](https://mlsanity.com/paper/2401.00320/) (2023)
- [Y-Drop: A Conductance based Dropout for fully connected layers](https://mlsanity.com/paper/2409.09088/) (2024)
- [Mechanistic Interpretability of Reinforcement Learning Agents](https://mlsanity.com/paper/2411.00867/) (2024)
- [C-SWAP: Explainability-Aware Structured Pruning for Efficient Neural Networks Compression](https://mlsanity.com/paper/2510.18636/) (2025)

## Abstract (arXiv)

We study the problem of explaining a rich class of behavioral properties of deep neural networks. Distinctively, our influence-directed explanations approach this problem by peering inside the network to identify neurons with high influence on a quantity and distribution of interest, using an axiomatically-justified influence measure, and then providing an interpretation for the concepts these neurons represent. We evaluate our approach by demonstrating a number of its unique capabilities on convolutional neural networks trained on ImageNet. Our evaluation demonstrates that influence-directed explanations (1) identify influential concepts that generalize across instances, (2) can be used to extract the "essence" of what the network learned about a class, and (3) isolate individual features the network uses to make decisions and distinguish related classes.