<ul><li>This paper discusses a scenario where target labels are not available, but related side information is present.</li><li>The authors propose a scoring model that combines representation learning, side information, and metric learning.</li><li>The model can be useful in various domains, such as healthcare, to create severity scores for diseases with undefined progression criteria.</li><li>The scoring system is tested on benchmark datasets and biomedical patient records.</li></ul>

Learning to Score

Discover more