# Label Distribution Learning Forests

arXiv: https://arxiv.org/abs/1702.06086 · HTML: https://mlsanity.com/paper/1702.06086/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2017.

## Built on by (most cited first, 25 of 25)

- [Learning Probabilistic Ordinal Embeddings for Uncertainty-Aware Regression](https://mlsanity.com/paper/2103.13629/) (2021)
- [Moving Window Regression: A Novel Approach to Ordinal Regression](https://mlsanity.com/paper/2203.13122/) (2022)
- [OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression](https://mlsanity.com/paper/2206.02338/) (2022)
- [Exploiting Multi-Label Correlation in Label Distribution Learning](https://mlsanity.com/paper/2308.01742/) (2023)
- [Improving Face-Based Age Estimation with Attention-Based Dynamic Patch Fusion](https://mlsanity.com/paper/2112.10167/) (2021)
- [Meta Ordinal Regression Forest for Medical Image Classification with Ordinal Labels](https://mlsanity.com/paper/2203.07725/) (2022)
- [TAA-GCN: A Temporally Aware Adaptive Graph Convolutional Network for Age Estimation](https://mlsanity.com/paper/2305.08779/) (2023)
- [A Survey on Ordinal Regression: Applications, Advances and Prospects](https://mlsanity.com/paper/2503.00952/) (2025)
- [MetaAge: Meta-Learning Personalized Age Estimators](https://mlsanity.com/paper/2207.05288/) (2022)
- [Noise-robust classification with hypergraph neural network](https://mlsanity.com/paper/2102.01934/) (2021)
- [Label Distribution Learning from Logical Label](https://mlsanity.com/paper/2303.06847/) (2023)
- [RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Inter-label Correlations](https://mlsanity.com/paper/2312.06343/) (2023)
- [Ordinal-Aware Calibration for Ordinal Classification](https://mlsanity.com/paper/2410.15658/) (2024)
- [GroupFace: Imbalanced Age Estimation Based on Multi-hop Attention Graph Convolutional Network and Group-aware Margin Optimization](https://mlsanity.com/paper/2412.11450/) (2024)
- [Relation-Aware Distribution Representation Network for Person Clustering with Multiple Modalities](https://mlsanity.com/paper/2308.00588/) (2023)
- [Transition Matrix Representation of Trees with Transposed Convolutions](https://mlsanity.com/paper/2202.10677/) (2022)
- [No Regularization is Needed: An Efficient and Effective Model for Incomplete Label Distribution Learning](https://mlsanity.com/paper/2308.07047/) (2023)
- [LRA-GNN: Latent Relation-Aware Graph Neural Network with Initial and Dynamic Residual for Facial Age Estimation](https://mlsanity.com/paper/2502.05423/) (2025)
- [Ranking-aware Reinforcement Learning for Ordinal Ranking](https://mlsanity.com/paper/2601.20585/) (2026)
- [Making CNNs Interpretable by Building Dynamic Sequential Decision Forests with Top-down Hierarchy Learning](https://mlsanity.com/paper/2106.02824/) (2021)
- [CORE: Learning Consistent Ordinal REpresentations for Image Ordinal Estimation](https://mlsanity.com/paper/2301.06122/) (2023)
- [Scalable Label Distribution Learning for Multi-Label Classification](https://mlsanity.com/paper/2311.16556/) (2023)
- [Label Distribution Learning using the Squared Neural Family on the Probability Simplex](https://mlsanity.com/paper/2412.07324/) (2024)
- [From Distance to Direction: Structure-aware Label-specific Feature Fusion for Label Distribution Learning](https://mlsanity.com/paper/2504.19374/) (2025)
- [Multi-View Semi-Supervised Label Distribution Learning with Local Structure Complementarity](https://mlsanity.com/paper/2510.13917/) (2025)

## Abstract (arXiv)

Label distribution learning (LDL) is a general learning framework, which assigns to an instance a distribution over a set of labels rather than a single label or multiple labels. Current LDL methods have either restricted assumptions on the expression form of the label distribution or limitations in representation learning, e.g., to learn deep features in an end-to-end manner. This paper presents label distribution learning forests (LDLFs) - a novel label distribution learning algorithm based on differentiable decision trees, which have several advantages: 1) Decision trees have the potential to model any general form of label distributions by a mixture of leaf node predictions. 2) The learning of differentiable decision trees can be combined with representation learning. We define a distribution-based loss function for a forest, enabling all the trees to be learned jointly, and show that an update function for leaf node predictions, which guarantees a strict decrease of the loss function, can be derived by variational bounding. The effectiveness of the proposed LDLFs is verified on several LDL tasks and a computer vision application, showing significant improvements to the state-of-the-art LDL methods.