# Trustworthy Representation Learning via Information Funnels and Bottlenecks

arXiv: https://arxiv.org/abs/2211.01446 · HTML: https://mlsanity.com/paper/2211.01446/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 36 references that are in the map.
- First posted on arXiv 2 Nov 2022.

## Builds on (most cited first, 14 of 14)

- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (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)
- [TabNet: Attentive Interpretable Tabular Learning](https://mlsanity.com/paper/1908.07442/) (2019)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [The Variational Fair Autoencoder](https://mlsanity.com/paper/1511.00830/) (2015)
- [Flexibly Fair Representation Learning by Disentanglement](https://mlsanity.com/paper/1906.02589/) (2019)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [Invariant Representations without Adversarial Training](https://mlsanity.com/paper/1805.09458/) (2018)
- [Learning Controllable Fair Representations](https://mlsanity.com/paper/1812.04218/) (2018)
- [A Variational Approach to Privacy and Fairness](https://mlsanity.com/paper/2006.06332/) (2020)
- [Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility](https://mlsanity.com/paper/2207.04895/) (2022)
- [Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and R'enyi Measures](https://mlsanity.com/paper/2206.10043/) (2022)

## Abstract (arXiv)

Ensuring trustworthiness in machine learning -- by balancing utility, fairness, and privacy -- remains a critical challenge, particularly in representation learning. In this work, we investigate a family of closely related information-theoretic objectives, including information funnels and bottlenecks, designed to extract invariant representations from data. We introduce the Conditional Privacy Funnel with Side-information (CPFSI), a novel formulation within this family, applicable in both fully and semi-supervised settings. Given the intractability of these objectives, we derive neural-network-based approximations via amortized variational inference. We systematically analyze the trade-offs between utility, invariance, and representation fidelity, offering new insights into the Pareto frontiers of these methods. Our results demonstrate that CPFSI effectively balances these competing objectives and frequently outperforms existing approaches. Furthermore, we show that by intervening on sensitive attributes in CPFSI's predictive posterior enhances fairness while maintaining predictive performance. Finally, we focus on the real-world applicability of these approaches, particularly for learning robust and fair representations from tabular datasets in data scarce-environments -- a modality where these methods are often especially relevant.