mlsanityData to 14 Oct 2026

Towards Best Practice in Explaining Neural Network Decisions with LRP

arXiv 1910.09840 ↗First posted 22 Oct 2019cs.LG cs.CV stat.MLcited by 70

Not on the map. Why?

Abstract (arXiv)

Within the last decade, neural network based predictors have demonstrated impressive - and at times super-human - capabilities. This performance is often paid for with an intransparent prediction process and thus has sparked numerous contributions in the novel field of explainable artificial intelligence (XAI). In this paper, we focus on a popular and widely used method of XAI, the Layer-wise Relevance Propagation (LRP). Since its initial proposition LRP has evolved as a method, and a best practice for applying the method has tacitly emerged, based however on humanly observed evidence alone. In this paper we investigate - and for the first time quantify - the effect of this current best practice on feedforward neural networks in a visual object detection setting. The results verify that the layer-dependent approach to LRP applied in recent literature better represents the model's reasoning, and at the same time increases the object localization and class discriminativity of LRP.

Key facts. Cited by 70 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 18; 2023: 17; 2024: 12; 2025: 7; 2026: 4.

70 papers.

Sort:

By area:

  1. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  2. 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
  3. 2022Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Datacited by 75
  4. 2021Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAycited by 55
  5. 2021This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagationcited by 43
  6. 2023The Meta-Evaluation Problem in Explainable AI: Identifying Reliable Estimators with MetaQuantuscited by 37
  7. 2022ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Modelcited by 34
  8. 2021NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weightscited by 28
  9. 2022Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geosciencecited by 28
  10. 2022Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergencecited by 25
  11. 2023Explainable AI for Time Series via Virtual Inspection Layerscited by 23
  12. 2023Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanationscited by 22
38 more
  1. 2023From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Spacecited by 20
  2. 2021Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark Datasetcited by 18
  3. 2021Explaining Bayesian Neural Networkscited by 18
  4. 2022Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanationscited by 17
  5. 2021A Survey on AI Assurancecited by 16
  6. 2021ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNscited by 15
  7. 2023Theoretical Behavior of XAI Methods in the Presence of Suppressor Variablescited by 12
  8. 2022Analysis of a Deep Learning Model for 12-Lead ECG Classification Reveals Learned Features Similar to Diagnostic Criteriacited by 11
  9. 2022Optimizing Explanations by Network Canonization and Hyperparameter Searchcited by 11
  10. 2024Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformerscited by 11
  11. 2025A Close Look at Decomposition-based XAI-Methods for Transformer Language Modelscited by 11
  12. 2024ExMap: Leveraging Explainability Heatmaps for Unsupervised Group Robustness to Spurious Correlationscited by 8
  13. 2022Explain to Not Forget: Defending Against Catastrophic Forgetting with XAIcited by 7
  14. 2025Bridging the Gap in XAI-Why Reliable Metrics Matter for Explainability and Compliancecited by 7
  15. 2021Focused LRP: Explainable AI for Face Morphing Attack Detectioncited by 6
  16. 2022Measurably Stronger Explanation Reliability via Model Canonizationcited by 6
  17. 2023Prototypical Self-Explainable Models Without Re-trainingcited by 6
  18. 2024Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decompositioncited by 6
  19. 2024Toward Understanding the Disagreement Problem in Neural Network Feature Attributioncited by 6
  20. 2022From Explanations to Segmentation: Using Explainable AI for Image Segmentationcited by 5
  21. 2024Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppressioncited by 5
  22. 2023A Survey of Explainable AI in Deep Visual Modeling: Methods and Metricscited by 4
  23. 2024Expected Grad-CAM: Towards gradient faithfulnesscited by 4
  24. 2021Interpretable Deep Learning for the Remote Characterisation of Ambulation in Multiple Sclerosis using Smartphonescited by 3
  25. 2021Challenges for cognitive decoding using deep learning methodscited by 3
  26. 2021Evaluating deep transfer learning for whole-brain cognitive decodingcited by 3
  27. 2022Local Interpretable Model Agnostic Shap Explanations for machine learning modelscited by 3
  28. 2022A Rigorous Study Of The Deep Taylor Decompositioncited by 3
  29. 2023Sanity checks and improvements for patch visualisation in prototype-based image classificationcited by 3
  30. 2023Robustness of Visual Explanations to Common Data Augmentationcited by 3
  31. 2023XAI-based Comparison of Input Representations for Audio Event Classificationcited by 3
  32. 2025On the Effectiveness of Methods and Metrics for Explainable AI in Remote Sensing Image Scene Classificationcited by 3
  33. 2022Comparing interpretation methods in mental state decoding analyses with deep learning modelscited by 2
  34. 2023Interpreting Deep Neural Networks with the Package innsightcited by 2
  35. 2023Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagationcited by 2
  36. 2024Locally Testing Model Detections for Semantic Global Conceptscited by 2
  37. 2022Brain Structural Saliency Over The Agescited by 1
  38. 2023Bridging the Gap: Gaze Events as Interpretable Concepts to Explain Deep Neural Sequence Modelscited by 1

50 most cited of 70 All 70 (JSON)