# Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration

arXiv: https://arxiv.org/abs/2103.12300 · HTML: https://mlsanity.com/paper/2103.12300/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 23 Mar 2021.

## Builds on (most cited first, 30 of 30)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables](https://mlsanity.com/paper/1611.00712/) (2016)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Large-Scale Study of Curiosity-Driven Learning](https://mlsanity.com/paper/1808.04355/) (2018)
- [ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning](https://mlsanity.com/paper/1605.02097/) (2016)
- [Information Dropout: Learning Optimal Representations Through Noisy Computation](https://mlsanity.com/paper/1611.01353/) (2016)
- [Invariant Representations without Adversarial Training](https://mlsanity.com/paper/1805.09458/) (2018)
- [Restricting the Flow: Information Bottlenecks for Attribution](https://mlsanity.com/paper/2001.00396/) (2020)
- [Episodic Curiosity through Reachability](https://mlsanity.com/paper/1810.02274/) (2018)
- [Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow](https://mlsanity.com/paper/1810.00821/) (2018)
- [Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck](https://mlsanity.com/paper/1910.12911/) (2019)
- [InfoBot: Transfer and Exploration via the Information Bottleneck](https://mlsanity.com/paper/1901.10902/) (2019)
- [The Conditional Entropy Bottleneck](https://mlsanity.com/paper/2002.05379/) (2020)
- [Nonlinear Information Bottleneck](https://mlsanity.com/paper/1705.02436/) (2017)
- [Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle](https://mlsanity.com/paper/1802.09766/) (2018)
- [Compressing Neural Networks using the Variational Information Bottleneck](https://mlsanity.com/paper/1802.10399/) (2018)
- [The deterministic information bottleneck](https://mlsanity.com/paper/1604.00268/) (2016)
- [Relevant sparse codes with variational information bottleneck](https://mlsanity.com/paper/1605.07332/) (2016)
- [CEB Improves Model Robustness](https://mlsanity.com/paper/2002.05380/) (2020)
- [The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget](https://mlsanity.com/paper/2004.11935/) (2020)

## Built on by (most cited first, 15 of 15)

- [Graph Structure Learning with Variational Information Bottleneck](https://mlsanity.com/paper/2112.08903/) (2021)
- [Improving Subgraph Recognition with Variational Graph Information Bottleneck](https://mlsanity.com/paper/2112.09899/) (2021)
- [Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning](https://mlsanity.com/paper/2110.14118/) (2021)
- [Representation Learning in Deep RL via Discrete Information Bottleneck](https://mlsanity.com/paper/2212.13835/) (2022)
- [LECO: Learnable Episodic Count for Task-Specific Intrinsic Reward](https://mlsanity.com/paper/2210.05409/) (2022)
- [Learning High-Order Relationships of Brain Regions](https://mlsanity.com/paper/2312.02203/) (2023)
- [Cauchy-Schwarz Divergence Information Bottleneck for Regression](https://mlsanity.com/paper/2404.17951/) (2024)
- [R2-Trans:Fine-Grained Visual Categorization with Redundancy Reduction](https://mlsanity.com/paper/2204.10095/) (2022)
- [Gated Information Bottleneck for Generalization in Sequential Environments](https://mlsanity.com/paper/2110.06057/) (2021)
- [IBCircuit: Towards Holistic Circuit Discovery with Information Bottleneck](https://mlsanity.com/paper/2602.22581/) (2026)
- [Sparsity-Inducing Categorical Prior Improves Robustness of the Information Bottleneck](https://mlsanity.com/paper/2203.02592/) (2022)
- [Understanding Encoder-Decoder Structures in Machine Learning Using Information Measures](https://mlsanity.com/paper/2405.20452/) (2024)
- [Structural Entropy Guided Probabilistic Coding](https://mlsanity.com/paper/2412.08841/) (2024)
- [Mixture of Balanced Information Bottlenecks for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2509.01804/) (2025)
- [Distilling a Modular Reservoir Through a Genomic Bottleneck](https://mlsanity.com/paper/2606.28380/) (2026)

## Abstract (arXiv)

We propose a novel information bottleneck (IB) method named Drop-Bottleneck, which discretely drops features that are irrelevant to the target variable. Drop-Bottleneck not only enjoys a simple and tractable compression objective but also additionally provides a deterministic compressed representation of the input variable, which is useful for inference tasks that require consistent representation. Moreover, it can jointly learn a feature extractor and select features considering each feature dimension's relevance to the target task, which is unattainable by most neural network-based IB methods. We propose an exploration method based on Drop-Bottleneck for reinforcement learning tasks. In a multitude of noisy and reward sparse maze navigation tasks in VizDoom (Kempka et al., 2016) and DMLab (Beattie et al., 2016), our exploration method achieves state-of-the-art performance. As a new IB framework, we demonstrate that Drop-Bottleneck outperforms Variational Information Bottleneck (VIB) (Alemi et al., 2017) in multiple aspects including adversarial robustness and dimensionality reduction.