mlsanityData to 14 Oct 2026

Influence-Directed Explanations for Deep Convolutional Networks

arXiv 1802.03788 ↗First posted 11 Feb 2018cs.LG cs.AI stat.MLcited by 31

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 5; 2023: 6; 2024: 9; 2025: 3; 2026: 1.

31 papers.

Sort:

By area:

  1. 2024Stochastic Concept Bottleneck Modelscited by 51
  2. 2021Consistent Counterfactuals for Deep Modelscited by 37
  3. 2024Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?cited by 28
  4. 2021Finding Discriminative Filters for Specific Degradations in Blind Super-Resolutioncited by 26
  5. 2024Optimal ablation for interpretabilitycited by 25
  6. 2021Selective Ensembles for Consistent Predictionscited by 23
  7. 2021Robust Models Are More Interpretable Because Attributions Look Normalcited by 21
  8. 2024Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restorationcited by 20
  9. 2024Decomposing and Editing Predictions by Modeling Model Computationcited by 19
  10. 2022The Manifold Hypothesis for Gradient-Based Explanationscited by 16
  11. 2021MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Datasetcited by 15
  12. 2022Debiasing Deep Chest X-Ray Classifiers using Intra- and Post-processing Methodscited by 15
19 more
  1. 2021Classification-Regression for Chart Comprehensioncited by 11
  2. 2022RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Modelcited by 11
  3. 2023Investigating the Effect of Misalignment on Membership Privacy in the White-box Settingcited by 9
  4. 2025Measuring Leakage in Concept-Based Methods: An Information Theoretic Approachcited by 9
  5. 2024Tree-Based Leakage Inspection and Control in Concept Bottleneck Modelscited by 8
  6. 2022On the Robustness of Explanations of Deep Neural Network Models: A Surveycited by 5
  7. 2023Generalizing Backpropagation for Gradient-Based Interpretabilitycited by 5
  8. 2021TorchEsegeta: Framework for Interpretability and Explainability of Image-based Deep Learning Modelscited by 4
  9. 2023Rationalizing Predictions by Adversarial Information Calibrationcited by 4
  10. 2023FedDefender: Backdoor Attack Defense in Federated Learningcited by 4
  11. 2024Validating Mechanistic Interpretations: An Axiomatic Approachcited by 4
  12. 2022Faithful Explanations for Deep Graph Modelscited by 2
  13. 2025RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restorationcited by 1
  14. 2023ExplainFix: Explainable Spatially Fixed Deep Networkscited by 0
  15. 2023DXAI: Explaining Classification by Image Decompositioncited by 0
  16. 2024Y-Drop: A Conductance based Dropout for fully connected layerscited by 0
  17. 2024Mechanistic Interpretability of Reinforcement Learning Agentscited by 0
  18. 2025C-SWAP: Explainability-Aware Structured Pruning for Efficient Neural Networks Compressioncited by 0
  19. 2026From Interpretability Methods to Interpretable Modelscited by 0