# Leveraging Group Classification with Descending Soft Labeling for Deep Imbalanced Regression

arXiv: https://arxiv.org/abs/2412.12327 · HTML: https://mlsanity.com/paper/2412.12327/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 63 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Builds on (most cited first, 26 of 26)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Large-Scale Long-Tailed Recognition in an Open World](https://mlsanity.com/paper/1904.05160/) (2019)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Deep Evidential Regression](https://mlsanity.com/paper/1910.02600/) (2019)
- [Delving into Deep Imbalanced Regression](https://mlsanity.com/paper/2102.09554/) (2021)
- [Remix: Rebalanced Mixup](https://mlsanity.com/paper/2007.03943/) (2020)
- [Self-supervised Learning is More Robust to Dataset Imbalance](https://mlsanity.com/paper/2110.05025/) (2021)
- [Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?](https://mlsanity.com/paper/2203.09081/) (2022)
- [Image Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2204.08610/) (2022)
- [Rank-N-Contrast: Learning Continuous Representations for Regression](https://mlsanity.com/paper/2210.01189/) (2022)
- [C-Mixup: Improving Generalization in Regression](https://mlsanity.com/paper/2210.05775/) (2022)
- [Posterior Re-calibration for Imbalanced Datasets](https://mlsanity.com/paper/2010.11820/) (2020)
- [RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression](https://mlsanity.com/paper/2205.15236/) (2022)
- [Improving Deep Regression with Ordinal Entropy](https://mlsanity.com/paper/2301.08915/) (2023)
- [ConR: Contrastive Regularizer for Deep Imbalanced Regression](https://mlsanity.com/paper/2309.06651/) (2023)
- [Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective](https://mlsanity.com/paper/2310.19360/) (2023)
- [Simplifying Neural Network Training Under Class Imbalance](https://mlsanity.com/paper/2312.02517/) (2023)
- [Deep Imbalanced Regression via Hierarchical Classification Adjustment](https://mlsanity.com/paper/2310.17154/) (2023)
- [Data Augmentation for Imbalanced Regression](https://mlsanity.com/paper/2302.09288/) (2023)
- [Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation](https://mlsanity.com/paper/2304.02064/) (2023)
- [Uncertainty Voting Ensemble for Imbalanced Deep Regression](https://mlsanity.com/paper/2305.15178/) (2023)
- [SupReMix: Supervised Contrastive Learning for Medical Imaging Regression with Mixup](https://mlsanity.com/paper/2309.16633/) (2023)
- [Variational Imbalanced Regression: Fair Uncertainty Quantification via Probabilistic Smoothing](https://mlsanity.com/paper/2306.06599/) (2023)

## Built on by (most cited first, 1 of 1)

- [Graph Domain Adaptation via Homophily-Agnostic Reconstructing Structure](https://mlsanity.com/paper/2602.07573/) (2026)

## Abstract (arXiv)

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.