Contrastive Learning for Semi-Supervised Deep Regression with Generalized Ordinal Rankings from Spectral Seriation

TL;DR

This paper introduces a semi-supervised contrastive learning approach for deep regression that leverages spectral seriation to recover ordinal rankings from both labeled and unlabeled data, improving representation and prediction accuracy.

Contribution

It extends contrastive regression to semi-supervised settings by incorporating spectral seriation for ordinal ranking, reducing reliance on labeled data and enhancing robustness.

Findings

Outperforms existing semi-supervised regression methods.

Provides theoretical guarantees for ordinal ranking accuracy.

Demonstrates robustness across various datasets.

Abstract

Contrastive learning methods enforce label distance relationships in feature space to improve representation capability for regression models. However, these methods highly depend on label information to correctly recover ordinal relationships of features, limiting their applications to semi-supervised regression. In this work, we extend contrastive regression methods to allow unlabeled data to be used in the semi-supervised setting, thereby reducing the dependence on costly annotations. Particularly we construct the feature similarity matrix with both labeled and unlabeled samples in a mini-batch to reflect inter-sample relationships, and an accurate ordinal ranking of involved unlabeled samples can be recovered through spectral seriation algorithms if the level of error is within certain bounds. The introduction of labeled samples above provides regularization of the ordinal ranking with guidance from the ground-truth label information, making the ranking more reliable. To reduce feature perturbations, we further utilize the dynamic programming algorithm to select robust features for the matrix construction. The recovered ordinal relationship is then used for contrastive learning on unlabeled samples, and we thus allow more data to be used for feature representation learning, thereby achieving more robust results. The ordinal rankings can also be used to supervise predictions on unlabeled samples, serving as an additional training signal. We provide theoretical guarantees and empirical verification through experiments on various datasets, demonstrating that our method can surpass existing state-of-the-art semi-supervised deep regression methods. Our code have been released on https://github.com/xmed-lab/CLSS.