# Interpreting and Boosting Dropout from a Game-Theoretic View

arXiv: https://arxiv.org/abs/2009.11729 · HTML: https://mlsanity.com/paper/2009.11729/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2020.

## Built on by (most cited first, 30 of 34)

- [MogaNet: Multi-order Gated Aggregation Network](https://mlsanity.com/paper/2211.03295/) (2022)
- [Discovering and Explaining the Representation Bottleneck of DNNs](https://mlsanity.com/paper/2111.06236/) (2021)
- [Defining and Quantifying the Emergence of Sparse Concepts in DNNs](https://mlsanity.com/paper/2111.06206/) (2021)
- [Explaining Deepfake Detection by Analysing Image Matching](https://mlsanity.com/paper/2207.09679/) (2022)
- [Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN](https://mlsanity.com/paper/2205.13943/) (2022)
- [Does a Neural Network Really Encode Symbolic Concepts?](https://mlsanity.com/paper/2302.13080/) (2023)
- [A Unified Game-Theoretic Interpretation of Adversarial Robustness](https://mlsanity.com/paper/2111.03536/) (2021)
- [A Game-Theoretic Taxonomy of Visual Concepts in DNNs](https://mlsanity.com/paper/2106.10938/) (2021)
- [Interpreting Attributions and Interactions of Adversarial Attacks](https://mlsanity.com/paper/2108.06895/) (2021)
- [Towards the Dynamics of a DNN Learning Symbolic Interactions](https://mlsanity.com/paper/2407.19198/) (2024)
- [Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs](https://mlsanity.com/paper/2304.13312/) (2023)
- [Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?](https://mlsanity.com/paper/2304.01083/) (2023)
- [Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?](https://mlsanity.com/paper/2105.10719/) (2021)
- [Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts](https://mlsanity.com/paper/2302.13095/) (2023)
- [Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models](https://mlsanity.com/paper/2305.01939/) (2023)
- [Visualizing the Emergence of Intermediate Visual Patterns in DNNs](https://mlsanity.com/paper/2111.03505/) (2021)
- [Diagnosing the Compositional Knowledge of Vision Language Models from a Game-Theoretic View](https://mlsanity.com/paper/2405.17201/) (2024)
- [The art of defense: letting networks fool the attacker](https://mlsanity.com/paper/2104.02963/) (2021)
- [Identifying Important Group of Pixels using Interactions](https://mlsanity.com/paper/2401.03785/) (2024)
- [Discovering the Representation Bottleneck of Graph Neural Networks](https://mlsanity.com/paper/2205.07266/) (2022)
- [Understanding Data Augmentation from a Robustness Perspective](https://mlsanity.com/paper/2311.12800/) (2023)
- [Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolution](https://mlsanity.com/paper/2402.18929/) (2024)
- [Game-Theoretic Understanding of Misclassification](https://mlsanity.com/paper/2210.03349/) (2022)
- [Technical Report: Quantifying and Analyzing the Generalization Power of a DNN](https://mlsanity.com/paper/2505.06993/) (2025)
- [Improving the Robustness and Generalization of Deep Neural Network with Confidence Threshold Reduction](https://mlsanity.com/paper/2206.00913/) (2022)
- [Why pre-training is beneficial for downstream classification tasks?](https://mlsanity.com/paper/2410.08455/) (2024)
- [The Interaction Bottleneck of Deep Neural Networks: Discovery, Proof, and Modulation](https://mlsanity.com/paper/2512.18607/) (2025)
- [A Unified Game-Theoretic Interpretation of Adversarial Robustness](https://mlsanity.com/paper/2103.07364/) (2021)
- [Excitement Surfeited Turns to Errors: Deep Learning Testing Framework Based on Excitable Neurons](https://mlsanity.com/paper/2202.07464/) (2022)
- [MixBoost: Improving the Robustness of Deep Neural Networks by Boosting Data Augmentation](https://mlsanity.com/paper/2212.04059/) (2022)

## 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.