Leveraging Group Classification with Descending Soft Labeling for Deep Imbalanced Regression

TL;DR

This paper introduces a novel approach for deep imbalanced regression by combining classification and regression through a divide-and-conquer strategy, utilizing group-aware contrastive learning and descending soft labels to better handle data imbalance and continuity.

Contribution

It proposes a new framework that decomposes DIR into classification and regression, employing group-aware contrastive loss and descending soft labels to improve performance on imbalanced data.

Findings

Effective in handling highly skewed target distributions

Improves regression accuracy through classification-guided regularization

Validated on real-world datasets with superior results

Abstract

Deep imbalanced regression (DIR), where the target values have a highly skewed distribution and are also continuous, is an intriguing yet under-explored problem in machine learning. While recent works have already shown that incorporating various classification-based regularizers can produce enhanced outcomes, the role of classification remains elusive in DIR. Moreover, such regularizers (e.g., contrastive penalties) merely focus on learning discriminative features of data, which inevitably results in ignorance of either continuity or similarity across the data. To address these issues, we first bridge the connection between the objectives of DIR and classification from a Bayesian perspective. Consequently, this motivates us to decompose the objective of DIR into a combination of classification and regression tasks, which naturally guides us toward a divide-and-conquer manner to solve the DIR problem. Specifically, by aggregating the data at nearby labels into the same groups, we introduce an ordinal group-aware contrastive learning loss along with a multi-experts regressor to tackle the different groups of data thereby maintaining the data continuity. Meanwhile, considering the similarity between the groups, we also propose a symmetric descending soft labeling strategy to exploit the intrinsic similarity across the data, which allows classification to facilitate regression more effectively. Extensive experiments on real-world datasets also validate the effectiveness of our method.