Towards Better Performance in Incomplete LDL: Addressing Data Imbalance

TL;DR

This paper introduces I extsuperscript{2}LDL, a novel framework for incomplete label distribution learning that effectively addresses data imbalance by decomposing label distributions into low-rank and sparse components, with strong theoretical and empirical validation.

Contribution

It proposes a new method that handles both incomplete labels and imbalanced distributions in LDL by matrix decomposition and optimization, with theoretical guarantees.

Findings

Outperforms existing InLDL methods on 15 datasets

Effectively captures structure of head and tail labels

Provides theoretical generalization bounds

Abstract

Label Distribution Learning (LDL) is a novel machine learning paradigm that addresses the problem of label ambiguity and has found widespread applications. Obtaining complete label distributions in real-world scenarios is challenging, which has led to the emergence of Incomplete Label Distribution Learning (InLDL). However, the existing InLDL methods overlook a crucial aspect of LDL data: the inherent imbalance in label distributions. To address this limitation, we propose \textbf{Incomplete and Imbalance Label Distribution Learning (I\(^2\)LDL)}, a framework that simultaneously handles incomplete labels and imbalanced label distributions. Our method decomposes the label distribution matrix into a low-rank component for frequent labels and a sparse component for rare labels, effectively capturing the structure of both head and tail labels. We optimize the model using the Alternating Direction Method of Multipliers (ADMM) and derive generalization error bounds via Rademacher complexity, providing strong theoretical guarantees. Extensive experiments on 15 real-world datasets demonstrate the effectiveness and robustness of our proposed framework compared to existing InLDL methods.