Conjunctive query embedding-based few-shot item recommendation

Jeong-Hoon Kim

doi:10.1016/j.neunet.2025.108342

Conjunctive query embedding-based few-shot item recommendation

2025-11-20

0

PRE

AI

DOI：10.1016/j.neunet.2025.108342

Original

Original request for help

Save

Abstract

En 中文

• We introduce a conjunctive query embedding model to learn user intent. • Our approach is particularly effective for item recommendation in sparse settings. • We propose the utilization of a query embedding method. • This method effectively incorporates uncertainty in conjunctive queries. • We demonstrate the effectiveness of our methodology through evaluation in sparse scenarios.

Conjunctive query embedding-based few-shot item recommendation

Abstract

Journal

Organization