UAKNN: Label Distribution Learning via Uncertainty-Aware KNN
This work addresses deployment and update challenges in LDL for industrial applications, though it appears incremental as it builds on existing KNN and uncertainty modeling approaches.
The paper tackles the problem of high training costs, limited scalability, and outlier sensitivity in Label Distribution Learning (LDL) by proposing UAKNN, a method combining KNN with uncertainty modeling, which achieves competitive performance on 12 benchmarks and fast inference speed suitable for industrial applications.
Label Distribution Learning (LDL) aims to characterize the polysemy of an instance by building a set of descriptive degrees corresponding to the instance. In recent years, researchers seek to model to obtain an accurate label distribution by using low-rank, label relations, expert experiences, and label uncertainty estimation. In general, these methods are based on algorithms with parameter learning in a linear (including kernel functions) or deep learning framework. However, these methods are difficult to deploy and update online due to high training costs, limited scalability, and outlier sensitivity. To address this problem, we design a novel LDL method called UAKNN, which has the advantages of the KNN algorithm with the benefits of uncertainty modeling. In addition, we provide solutions to the dilemma of existing work on extremely label distribution spaces. Extensive experiments demonstrate that our method is significantly competitive on 12 benchmarks and that the inference speed of the model is well-suited for industrial-level applications.