mlsanityData to 7 Oct 2026

Detecting Statistical Interactions from Neural Network Weights

arXiv 1705.04977 ↗First posted 14 May 2017stat.ML cs.LGcited by 80

Not on the map. Why?

Abstract (arXiv)

Interpreting neural networks is a crucial and challenging task in machine learning. In this paper, we develop a novel framework for detecting statistical interactions captured by a feedforward multilayer neural network by directly interpreting its learned weights. Depending on the desired interactions, our method can achieve significantly better or similar interaction detection performance compared to the state-of-the-art without searching an exponential solution space of possible interactions. We obtain this accuracy and efficiency by observing that interactions between input features are created by the non-additive effect of nonlinear activation functions, and that interacting paths are encoded in weight matrices. We demonstrate the performance of our method and the importance of discovered interactions via experimental results on both synthetic datasets and real-world application datasets.

Key facts. Cited by 80 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 8; 2023: 22; 2024: 11; 2025: 10; 2026: 12.

80 papers.

Sort:

By area:

  1. 2023RanPAC: Random Projections and Pre-trained Models for Continual Learningcited by 162
  2. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  3. 2022Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questionscited by 116
  4. 2021NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learningcited by 88
  5. 2023Quantifying & Modeling Multimodal Interactions: An Information Decomposition Frameworkcited by 81
  6. 2022Faith-Shap: The Faithful Shapley Interaction Indexcited by 68
  7. 2023Explaining black box text modules in natural language with language modelscited by 61
  8. 2023SHAP-IQ: Unified Approximation of any-order Shapley Interactionscited by 50
  9. 2021Discovering and Explaining the Representation Bottleneck of DNNscited by 42
  10. 2022MultiViz: Towards Visualizing and Understanding Multimodal Modelscited by 36
  11. 2021Toward Explainable AI for Regression Modelscited by 30
  12. 2024KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley Interactionscited by 22
38 more
  1. 2023MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Expertscited by 21
  2. 2023Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applicationscited by 20
  3. 2024MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignmentcited by 18
  4. 2021A Unified Game-Theoretic Interpretation of Adversarial Robustnesscited by 17
  5. 2021MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Datasetcited by 15
  6. 2021Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution Viewcited by 15
  7. 2023Explanations of Black-Box Models based on Directional Feature Interactionscited by 15
  8. 2023Improving Neural Additive Models with Bayesian Principlescited by 15
  9. 2023Efficient XAI Techniques: A Taxonomic Surveycited by 14
  10. 2023Hiformer: Heterogeneous Feature Interactions Learning with Transformers for Recommender Systemscited by 14
  11. 2021Interpreting Attributions and Interactions of Adversarial Attackscited by 13
  12. 2021Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?cited by 10
  13. 2023Multimodal Fusion Interactions: A Study of Human and Automatic Quantificationcited by 9
  14. 2023Feature Interactions Reveal Linguistic Structure in Language Modelscited by 8
  15. 2021Interpretable Artificial Intelligence through the Lens of Feature Interactioncited by 5
  16. 2023Exploring the cloud of feature interaction scores in a Rashomon setcited by 5
  17. 2023SmoothHess: ReLU Network Feature Interactions via Stein's Lemmacited by 5
  18. 2021Mixture of Linear Models Co-supervised by Deep Neural Networkscited by 4
  19. 2022A Comprehensive Survey on Automated Machine Learning for Recommendationscited by 4
  20. 2022Discovering the Representation Bottleneck of Graph Neural Networkscited by 4
  21. 2023How to address monotonicity for model risk management?cited by 4
  22. 2025An Explainable Biomedical Foundation Model via Large-Scale Concept-Enhanced Vision-Language Pre-trainingcited by 4
  23. 2025Tensor Product Neural Networks for Functional ANOVA Modelcited by 4
  24. 2025Interpretable Retinal Disease Prediction Using Biology-Informed Heterogeneous Graph Representationscited by 4
  25. 2025Massively Multimodal Foundation Models: A Framework for Capturing Interactions with Specialized Mixture-of-Expertscited by 4
  26. 2024Practical Attribution Guidance for Rashomon Setscited by 3
  27. 2024Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributionscited by 3
  28. 2022Detection of Interacting Variables for Generalized Linear Models via Neural Networkscited by 2
  29. 2023Distributing Synergy Functions: Unifying Game-Theoretic Interaction Methods for Machine-Learning Explainabilitycited by 2
  30. 2024META-ANOVA: Screening interactions for interpretable machine learningcited by 2
  31. 2025Tree-like Pairwise Interaction Networkscited by 2
  32. 2026Normalized Relevance Measure as a Unifying Framework to Explain Neural Network Latent Structurescited by 2
  33. 2021Random Intersection Chainscited by 1
  34. 2021Interpreting and improving deep-learning models with reality checkscited by 1
  35. 2022PGX: A Multi-level GNN Explanation Framework Based on Separate Knowledge Distillation Processescited by 1
  36. 2023The Weighted M"obius Score: A Unified Framework for Feature Attributioncited by 1
  37. 2023Towards Assumption-free Bias Mitigationcited by 1
  38. 2023Towards Attributions of Input Variables in a Coalitioncited by 1

50 most cited of 80 All 80 (JSON)