Can One Embedding Fit All? A Multi-Interest Learning Paradigm Towards Improving User Interest Diversity Fairness
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913238441000960 |
|---|---|
| author | Zhao, Yuying Xu, Minghua Chen, Huiyuan Chen, Yuzhong Cai, Yiwei Islam, Rashidul Wang, Yu Derr, Tyler |
| author_facet | Zhao, Yuying Xu, Minghua Chen, Huiyuan Chen, Yuzhong Cai, Yiwei Islam, Rashidul Wang, Yu Derr, Tyler |
| contents | Recommender systems (RSs) have gained widespread applications across various domains owing to the superior ability to capture users' interests. However, the complexity and nuanced nature of users' interests, which span a wide range of diversity, pose a significant challenge in delivering fair recommendations. In practice, user preferences vary significantly; some users show a clear preference toward certain item categories, while others have a broad interest in diverse ones. Even though it is expected that all users should receive high-quality recommendations, the effectiveness of RSs in catering to this disparate interest diversity remains under-explored.
In this work, we investigate whether users with varied levels of interest diversity are treated fairly. Our empirical experiments reveal an inherent disparity: users with broader interests often receive lower-quality recommendations. To mitigate this, we propose a multi-interest framework that uses multiple (virtual) interest embeddings rather than single ones to represent users. Specifically, the framework consists of stacked multi-interest representation layers, which include an interest embedding generator that derives virtual interests from shared parameters, and a center embedding aggregator that facilitates multi-hop aggregation. Experiments demonstrate the effectiveness of the framework in achieving better trade-off between fairness and utility across various datasets and backbones. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13495 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Can One Embedding Fit All? A Multi-Interest Learning Paradigm Towards Improving User Interest Diversity Fairness Zhao, Yuying Xu, Minghua Chen, Huiyuan Chen, Yuzhong Cai, Yiwei Islam, Rashidul Wang, Yu Derr, Tyler Information Retrieval Recommender systems (RSs) have gained widespread applications across various domains owing to the superior ability to capture users' interests. However, the complexity and nuanced nature of users' interests, which span a wide range of diversity, pose a significant challenge in delivering fair recommendations. In practice, user preferences vary significantly; some users show a clear preference toward certain item categories, while others have a broad interest in diverse ones. Even though it is expected that all users should receive high-quality recommendations, the effectiveness of RSs in catering to this disparate interest diversity remains under-explored. In this work, we investigate whether users with varied levels of interest diversity are treated fairly. Our empirical experiments reveal an inherent disparity: users with broader interests often receive lower-quality recommendations. To mitigate this, we propose a multi-interest framework that uses multiple (virtual) interest embeddings rather than single ones to represent users. Specifically, the framework consists of stacked multi-interest representation layers, which include an interest embedding generator that derives virtual interests from shared parameters, and a center embedding aggregator that facilitates multi-hop aggregation. Experiments demonstrate the effectiveness of the framework in achieving better trade-off between fairness and utility across various datasets and backbones. |
| title | Can One Embedding Fit All? A Multi-Interest Learning Paradigm Towards Improving User Interest Diversity Fairness |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2402.13495 |