mlsanityData to 14 Oct 2026

Defining and Extracting generalizable interaction primitives from DNNs

arXiv 2401.16318 ↗First posted 29 Jan 2024cs.LG cs.AI cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Faithfully summarizing the knowledge encoded by a deep neural network (DNN) into a few symbolic primitive patterns without losing much information represents a core challenge in explainable AI. To this end, Ren et al. (2024) have derived a series of theorems to prove that the inference score of a DNN can be explained as a small set of interactions between input variables. However, the lack of generalization power makes it still hard to consider such interactions as faithful primitive patterns encoded by the DNN. Therefore, given different DNNs trained for the same task, we develop a new method to extract interactions that are shared by these DNNs. Experiments show that the extracted interactions can better reflect common knowledge shared by different DNNs.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 23 of its 32 references that are in the map. First posted on arXiv 29 Jan 2024.

Builds on

23 of 32 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  7. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  8. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  9. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  10. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
  11. 2015Understanding Neural Networks Through Deep Visualizationcited by 334
  12. 2023Rosetta Neurons: Mining the Common Units in a Model Zoocited by 46
11 more
  1. 2021Discovering and Explaining the Representation Bottleneck of DNNscited by 42
  2. 2021Defining and Quantifying the Emergence of Sparse Concepts in DNNscited by 36
  3. 2023Does a Neural Network Really Encode Symbolic Concepts?cited by 27
  4. 2023Explaining Generalization Power of a DNN Using Interactive Conceptscited by 25
  5. 2022Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferabilitycited by 12
  6. 2023Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNscited by 12
  7. 2023Understanding and Unifying Fourteen Attribution Methods with Taylor Interactionscited by 11
  8. 2023Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?cited by 11
  9. 2021Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?cited by 10
  10. 2023Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Modelscited by 8
  11. 2023Explaining How a Neural Network Play the Go Game and Let People Learncited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 3; 2026: 5.

14 papers.

Sort:

By area:

  1. 2024Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Surveycited by 52
  2. 2024Towards the Dynamics of a DNN Learning Symbolic Interactionscited by 13
  3. 2024Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Featurescited by 5
  4. 2024Quantifying In-Context Reasoning Effects and Memorization Effects in LLMscited by 3
  5. 2025Revisiting Generalization Power of a DNN in Terms of Symbolic Interactionscited by 2
  6. 2025Technical Report: Quantifying and Analyzing the Generalization Power of a DNNcited by 2
  7. 2024Evaluating the Correctness of Inference Patterns Used by LLMs for Judgmentcited by 1
  8. 2026Cross-LLM Consistency in Inference: Evidence from Shared Interactionscited by 1
  9. 2024Disentangling Regional Primitives for Image Generationcited by 0
  10. 2025Towards provable probabilistic safety for scalable embodied AI systemscited by 0
  11. 2026BACH-V: Bridging Abstract and Concrete Human-Values in Large Language Modelscited by 0
  12. 2026Reconciling Contradictory Views on the Effectiveness of SFT in LLMs: An Interaction Perspectivecited by 0
2 more
  1. 2026A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactionscited by 0
  2. 2026Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactionscited by 0