Countering Mainstream Bias via End-to-End Adaptive Local Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910409519267840 |
|---|---|
| author | Pan, Jinhao Zhu, Ziwei Wang, Jianling Lin, Allen Caverlee, James |
| author_facet | Pan, Jinhao Zhu, Ziwei Wang, Jianling Lin, Allen Caverlee, James |
| contents | Collaborative filtering (CF) based recommendations suffer from mainstream bias -- where mainstream users are favored over niche users, leading to poor recommendation quality for many long-tail users. In this paper, we identify two root causes of this mainstream bias: (i) discrepancy modeling, whereby CF algorithms focus on modeling mainstream users while neglecting niche users with unique preferences; and (ii) unsynchronized learning, where niche users require more training epochs than mainstream users to reach peak performance. Targeting these causes, we propose a novel end-To-end Adaptive Local Learning (TALL) framework to provide high-quality recommendations to both mainstream and niche users. TALL uses a loss-driven Mixture-of-Experts module to adaptively ensemble experts to provide customized local models for different users. Further, it contains an adaptive weight module to synchronize the learning paces of different users by dynamically adjusting weights in the loss. Extensive experiments demonstrate the state-of-the-art performance of the proposed model. Code and data are provided at \url{https://github.com/JP-25/end-To-end-Adaptive-Local-Leanring-TALL-} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_08887 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Countering Mainstream Bias via End-to-End Adaptive Local Learning Pan, Jinhao Zhu, Ziwei Wang, Jianling Lin, Allen Caverlee, James Information Retrieval Machine Learning Collaborative filtering (CF) based recommendations suffer from mainstream bias -- where mainstream users are favored over niche users, leading to poor recommendation quality for many long-tail users. In this paper, we identify two root causes of this mainstream bias: (i) discrepancy modeling, whereby CF algorithms focus on modeling mainstream users while neglecting niche users with unique preferences; and (ii) unsynchronized learning, where niche users require more training epochs than mainstream users to reach peak performance. Targeting these causes, we propose a novel end-To-end Adaptive Local Learning (TALL) framework to provide high-quality recommendations to both mainstream and niche users. TALL uses a loss-driven Mixture-of-Experts module to adaptively ensemble experts to provide customized local models for different users. Further, it contains an adaptive weight module to synchronize the learning paces of different users by dynamically adjusting weights in the loss. Extensive experiments demonstrate the state-of-the-art performance of the proposed model. Code and data are provided at \url{https://github.com/JP-25/end-To-end-Adaptive-Local-Leanring-TALL-} |
| title | Countering Mainstream Bias via End-to-End Adaptive Local Learning |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2404.08887 |