# Information Competing Process for Learning Diversified Representations

arXiv: https://arxiv.org/abs/1906.01288 · HTML: https://mlsanity.com/paper/1906.01288/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2019.

## Built on by (most cited first, 6 of 6)

- [Image-to-image Translation via Hierarchical Style Disentanglement](https://mlsanity.com/paper/2103.01456/) (2021)
- [Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utility](https://mlsanity.com/paper/2207.04895/) (2022)
- [Multi-Modal Mutual Information Maximization: A Novel Approach for Unsupervised Deep Cross-Modal Hashing](https://mlsanity.com/paper/2112.06489/) (2021)
- [Competing Mutual Information Constraints with Stochastic Competition-based Activations for Learning Diversified Representations](https://mlsanity.com/paper/2201.03624/) (2022)
- [Learning Self-Regularized Adversarial Views for Self-Supervised Vision Transformers](https://mlsanity.com/paper/2210.08458/) (2022)
- [Deep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognition](https://mlsanity.com/paper/2404.02696/) (2024)

## Abstract (arXiv)

Learning representations with diversified information remains as an open problem. Towards learning diversified representations, a new approach, termed Information Competing Process (ICP), is proposed in this paper. Aiming to enrich the information carried by feature representations, ICP separates a representation into two parts with different mutual information constraints. The separated parts are forced to accomplish the downstream task independently in a competitive environment which prevents the two parts from learning what each other learned for the downstream task. Such competing parts are then combined synergistically to complete the task. By fusing representation parts learned competitively under different conditions, ICP facilitates obtaining diversified representations which contain rich information. Experiments on image classification and image reconstruction tasks demonstrate the great potential of ICP to learn discriminative and disentangled representations in both supervised and self-supervised learning settings.