Title:
RECOMMENDATION SYSTEM WITH ADAPTIVE WEIGHTED BAYSIAN PERSONALIZED RANKING LOSS
Document Type and Number:
WIPO Patent Application WO/2022/166125
Kind Code:
A1
Abstract:
Recommendation system for processing an input dataset that identifies a set of users, a set of items, and user-item interaction data. A plurality of unique triplets are identified based on the input dataset, wherein each triplet includes: a positive user-item pair; and a negative user-item pair. Over a plurality of training iterations system parameters are learned, including (i) a set of model embeddings for generating respective user-item relevance scores for the positive user-item pairs and the negative user-item pairs; and (ii) weight parameters for each of the triplets. The learning is configured to jointly optimize the model embeddings and the weight parameters to reach a learning objective that is based on weighted difference values determined for the triplets.
Inventors:
WU HAOLUN (CA)
MA CHEN (CA)
ZHANG YINGXUE (CA)
MA CHEN (CA)
ZHANG YINGXUE (CA)
Application Number:
PCT/CN2021/107743
Publication Date:
August 11, 2022
Filing Date:
July 22, 2021
Export Citation:
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
G06N3/08; G06F16/9535
Foreign References:
| CN112199589A | 2021-01-08 | |||
| CN111104601A | 2020-05-05 | |||
| US20190251446A1 | 2019-08-15 | |||
| US20200258132A1 | 2020-08-13 |
Download PDF: