# Refining the Information Bottleneck via Adversarial Information Separation

arXiv: https://arxiv.org/abs/2602.06549 · HTML: https://mlsanity.com/paper/2602.06549/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 50 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [Feature Purification: How Adversarial Training Performs Robust Deep Learning](https://mlsanity.com/paper/2005.10190/) (2020)
- [How Does Information Bottleneck Help Deep Learning?](https://mlsanity.com/paper/2305.18887/) (2023)
- [Invariant Information Bottleneck for Domain Generalization](https://mlsanity.com/paper/2106.06333/) (2021)
- [Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle](https://mlsanity.com/paper/1802.09766/) (2018)
- [Disentanglement via Latent Quantization](https://mlsanity.com/paper/2305.18378/) (2023)
- [Learning Independent Features with Adversarial Nets for Non-linear ICA](https://mlsanity.com/paper/1710.05050/) (2017)
- [Commutative Lie Group VAE for Disentanglement Learning](https://mlsanity.com/paper/2106.03375/) (2021)
- [Disentangled Information Bottleneck](https://mlsanity.com/paper/2012.07372/) (2020)
- [Approximating mutual information of high-dimensional variables using learned representations](https://mlsanity.com/paper/2409.02732/) (2024)
- [Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning](https://mlsanity.com/paper/2404.10282/) (2024)
- [Representation Learning with Conditional Information Flow Maximization](https://mlsanity.com/paper/2406.05510/) (2024)

## Built on by (most cited first, 1 of 1)

- [IB-HFN: Information Bottleneck-Driven SAR-Optical Fusion Network for High-Fidelity Cloud Removal](https://mlsanity.com/paper/2606.09347/) (2026)

## Abstract (arXiv)

Generalizing from limited data is particularly critical for models in domains such as material science, where task-relevant features in experimental datasets are often heavily confounded by measurement noise and experimental artifacts. Standard regularization techniques fail to precisely separate meaningful features from noise, while existing adversarial adaptation methods are limited by their reliance on explicit separation labels. To address this challenge, we propose the Adversarial Information Separation Framework (AdverISF), which isolates task-relevant features from noise without requiring explicit supervision. AdverISF introduces a self-supervised adversarial mechanism to enforce statistical independence between task-relevant features and noise representations. It further employs a multi-layer separation architecture that progressively recycles noise information across feature hierarchies to recover features inadvertently discarded as noise, thereby enabling finer-grained feature extraction. Extensive experiments demonstrate that AdverISF outperforms state-of-the-art methods in data-scarce scenarios. In addition, evaluations on real-world material design tasks show that it achieves superior generalization performance.