PPNW: personalized pairwise novelty loss weighting for novel recommendation
| Autor: | Kachun Lo, Tsukasa Ishigaki |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Focus (computing)
Computer science business.industry media_common.quotation_subject Novelty 02 engineering and technology Recommender system Machine learning computer.software_genre Weighting Human-Computer Interaction Artificial Intelligence Hardware and Architecture Robustness (computer science) 020204 information systems 0202 electrical engineering electronic engineering information engineering Collaborative filtering Pairwise comparison Artificial intelligence business Function (engineering) computer Software Information Systems media_common |
| Zdroj: | Knowledge and Information Systems. 63:1117-1148 |
| ISSN: | 0219-3116 0219-1377 |
| DOI: | 10.1007/s10115-021-01546-8 |
| Popis: | Most works of recommender systems focus on providing users with highly accurate item predictions based on the assumption that accurate suggestions can best satisfy users. However, accuracy-focused models also create great system bias towards popular items and, as a result, unpopular items rarely get recommended and will stay as “cold items” forever. Both users and item providers will suffer in such scenario. To promote item novelty, which plays a crucial role in system robustness and diversity, previous studies focus mainly on re-ranking a top-N list generated by an accuracy-focused base model. The re-ranking algorithm is thus completely independent of the base model. Eventually, these frameworks are essentially limited by the base model and the separated 2 stages cause greater complication and inefficiency in providing novel suggestions. In this work, we propose a personalized pairwise novelty weighting framework for BPR loss function, which covers the limitations of BPR and effectively improves novelty with negligible decrease in accuracy. Base model will be guided by the novelty-aware loss weights to learn user preference and to generate novel top-N list in only 1 stage. Comprehensive experiments on 3 public datasets show that our approach effectively promotes novelty with almost no decrease in accuracy. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink