Sample Selection via Contrastive Fragmentation for Noisy Label Regression

TL;DR

This paper introduces ConFrag, a novel contrastive fragmentation method for noisy label regression that improves sample selection and model robustness across diverse datasets.

Contribution

The paper proposes a new contrastive fragmentation framework that enhances sample selection and noise robustness in regression with noisy labels.

Findings

Outperforms 14 state-of-the-art methods

Robust against symmetric and Gaussian label noise

Effective across multiple diverse datasets

Abstract

As with many other problems, real-world regression is plagued by the presence of noisy labels, an inevitable issue that demands our attention. Fortunately, much real-world data often exhibits an intrinsic property of continuously ordered correlations between labels and features, where data points with similar labels are also represented with closely related features. In response, we propose a novel approach named ConFrag, where we collectively model the regression data by transforming them into disjoint yet contrasting fragmentation pairs. This enables the training of more distinctive representations, enhancing the ability to select clean samples. Our ConFrag framework leverages a mixture of neighboring fragments to discern noisy labels through neighborhood agreement among expert feature extractors. We extensively perform experiments on six newly curated benchmark datasets of diverse domains, including age prediction, price prediction, and music production year estimation. We also introduce a metric called Error Residual Ratio (ERR) to better account for varying degrees of label noise. Our approach consistently outperforms fourteen state-of-the-art baselines, being robust against symmetric and random Gaussian label noise.