Fig 1.
A real-world example of category-diversified and accurate recommendation of CatDive.
Each rectangle represents a book; its color indicates the category, and the number inside denotes the book index. CatDive recommends items of diverse categories and also predicts the ground-truth item, while SASRec fails, recommending items only in the user’s favorite category.
Table 1.
Table of symbols.
Fig 2.
Overview of CatDive, which consists of training and reranking phases.
Table 2.
Summary of datasets.
Fig 3.
Performance of CatDive and competitors.
CatDive is the closest to the best point with the highest category diversity and accuracy among all datasets.
Fig 4.
Performance of CatDive applied to different backbone models.
CatDive improves both category diversity and accuracy when applied to all models.
Table 3.
Ablation study of multi-embedding (ME) and preference-confidence based negative sampling (NS).
‘Improv.’ next to each component indicates the improvement relative to the original backbone model. The best is marked bold and the second best is underlined.
Table 4.
Recommendation by CatDive and SASrec in Amazon books.
CatDive recommends books of diverse categories while SASRec recommends only a single category. SF & Fan and Lit & Fic stand for Science Fiction & Fantasy and Literature & Fiction, respectively. The ground-truth items are marked in bold.