Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

by   Yaodong Yu, et al.

To learn intrinsic low-dimensional structures from high-dimensional data that most discriminate between classes, we propose the principle of Maximal Coding Rate Reduction (MCR^2), an information-theoretic measure that maximizes the coding rate difference between the whole dataset and the sum of each individual class. We clarify its relationships with most existing frameworks such as cross-entropy, information bottleneck, information gain, contractive and contrastive learning, and provide theoretical guarantees for learning diverse and discriminative features. The coding rate can be accurately computed from finite samples of degenerate subspace-like distributions and can learn intrinsic representations in supervised, self-supervised, and unsupervised settings in a unified manner. Empirically, the representations learned using this principle alone are significantly more robust to label corruptions in classification than those using cross-entropy, and can lead to state-of-the-art results in clustering mixed data from self-learned invariant features.


Efficient Maximal Coding Rate Reduction by Variational Forms

The principle of Maximal Coding Rate Reduction (MCR^2) has recently been...

Label Contrastive Coding based Graph Neural Network for Graph Classification

Graph classification is a critical research problem in many applications...

Integrating Auxiliary Information in Self-supervised Learning

This paper presents to integrate the auxiliary information (e.g., additi...

Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning

Detecting Out-of-Domain (OOD) or unknown intents from user queries is es...

SCEHR: Supervised Contrastive Learning for Clinical Risk Prediction using Electronic Health Records

Contrastive learning has demonstrated promising performance in image and...

ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction

This work attempts to provide a plausible theoretical framework that aim...

Supervised Deep Sparse Coding Networks

In this paper, we describe the deep sparse coding network (SCN), a novel...