mlsanityData to 7 Oct 2026

Interpreting and Boosting Dropout from a Game-Theoretic View

arXiv 2009.11729 ↗First posted 24 Sep 2020cs.LG cs.AI cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

This paper aims to understand and improve the utility of the dropout operation from the perspective of game-theoretic interactions. We prove that dropout can suppress the strength of interactions between input variables of deep neural networks (DNNs). The theoretic proof is also verified by various experiments. Furthermore, we find that such interactions were strongly related to the over-fitting problem in deep learning. Thus, the utility of dropout can be regarded as decreasing interactions to alleviate the significance of over-fitting. Based on this understanding, we propose an interaction loss to further improve the utility of dropout. Experimental results have shown that the interaction loss can effectively improve the utility of dropout and boost the performance of DNNs.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 8; 2023: 6; 2024: 6; 2025: 3; 2026: 2.

34 papers.

Sort:

By area:

  1. 2022MogaNet: Multi-order Gated Aggregation Networkcited by 59
  2. 2021Discovering and Explaining the Representation Bottleneck of DNNscited by 42
  3. 2021Defining and Quantifying the Emergence of Sparse Concepts in DNNscited by 36
  4. 2022Explaining Deepfake Detection by Analysing Image Matchingcited by 34
  5. 2022Architecture-Agnostic Masked Image Modeling -- From ViT back to CNNcited by 31
  6. 2023Does a Neural Network Really Encode Symbolic Concepts?cited by 27
  7. 2021A Unified Game-Theoretic Interpretation of Adversarial Robustnesscited by 17
  8. 2021A Game-Theoretic Taxonomy of Visual Concepts in DNNscited by 16
  9. 2021Interpreting Attributions and Interactions of Adversarial Attackscited by 13
  10. 2024Towards the Dynamics of a DNN Learning Symbolic Interactionscited by 13
  11. 2023Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?cited by 11
  12. 2021Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?cited by 10
22 more
  1. 2023Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNscited by 10
  2. 2023Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Conceptscited by 9
  3. 2023Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Modelscited by 8
  4. 2021Visualizing the Emergence of Intermediate Visual Patterns in DNNscited by 7
  5. 2024Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic Viewcited by 7
  6. 2021The art of defense: letting networks fool the attackercited by 6
  7. 2024Identifying Important Group of Pixels using Interactionscited by 5
  8. 2022Discovering the Representation Bottleneck of Graph Neural Networkscited by 4
  9. 2023Understanding Data Augmentation from a Robustness Perspectivecited by 3
  10. 2024Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolutioncited by 3
  11. 2022Improving the Robustness and Generalization of Deep Neural Network with Confidence Threshold Reductioncited by 1
  12. 2022Game-Theoretic Understanding of Misclassificationcited by 1
  13. 2024Why pre-training is beneficial for downstream classification tasks?cited by 1
  14. 2025Technical Report: Quantifying and Analyzing the Generalization Power of a DNNcited by 1
  15. 2025The Interaction Bottleneck of Deep Neural Networks: Discovery, Proof, and Modulationcited by 1
  16. 2021A Unified Game-Theoretic Interpretation of Adversarial Robustnesscited by 0
  17. 2022Excitement Surfeited Turns to Errors: Deep Learning Testing Framework Based on Excitable Neuronscited by 0
  18. 2022MixBoost: Improving the Robustness of Deep Neural Networks by Boosting Data Augmentationcited by 0
  19. 2024Disentangling Regional Primitives for Image Generationcited by 0
  20. 2025Game-Theoretic Gradient Control for Robust Neural Network Trainingcited by 0
  21. 2026Understanding Generalization through Decision Pattern Shiftcited by 0
  22. 2026A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactionscited by 0