# From Distance to Direction: Structure-aware Label-specific Feature Fusion for Label Distribution Learning

arXiv: https://arxiv.org/abs/2504.19374 · HTML: https://mlsanity.com/paper/2504.19374/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 38 references that are in the map.
- First posted on arXiv 27 Apr 2025.

## Builds on (most cited first, 5 of 5)

- [Label Distribution Learning](https://mlsanity.com/paper/1408.6027/) (2014)
- [Deep Label Distribution Learning with Label Ambiguity](https://mlsanity.com/paper/1611.01731/) (2016)
- [Label Distribution Learning Forests](https://mlsanity.com/paper/1702.06086/) (2017)
- [SCUT-FBP: A Benchmark Dataset for Facial Beauty Perception](https://mlsanity.com/paper/1511.02459/) (2015)
- [Label Distribution Learning for Generalizable Multi-source Person Re-identification](https://mlsanity.com/paper/2204.05903/) (2022)

## Abstract (arXiv)

Label distribution learning (LDL) is an emerging learning paradigm designed to capture the relative importance of labels for each instance. Label-specific features (LSFs), constructed by LIFT, have proven effective for learning tasks with label ambiguity by leveraging clustering-based prototypes for each label to re-characterize instances. However, directly introducing LIFT into LDL tasks can be suboptimal, as the prototypes it collects primarily reflect intra-cluster relationships while neglecting cross-cluster interactions. Additionally, constructing LSFs using multi-perspective information, rather than relying solely on Euclidean distance, provides a more robust and comprehensive representation of instances, mitigating noise and bias that may arise from a single distance perspective. To address these limitations, we introduce Structural Anchor Points (SAPs) to capture inter-cluster interactions. This leads to a novel LSFs construction strategy, LIFT-SAP, which enhances LIFT by integrating both distance and directional information of each instance relative to SAPs. Furthermore, we propose a novel LDL algorithm, Label Distribution Learning via Label-specifIc FeaTure with SAPs (LDL-LIFT-SAP), which unifies multiple label description degrees predicted from different LSF spaces into a cohesive label distribution. Extensive experiments on 15 real-world datasets demonstrate the effectiveness of LIFT-SAP over LIFT, as well as the superiority of LDL-LIFT-SAP compared to seven other well-established algorithms.