FeDecider: An LLM-Based Framework for Federated Cross-Domain Recommendation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915803767504896 |
|---|---|
| author | He, Xinrui Li, Ting-Wei Wei, Tianxin Ning, Xuying He, Xinyu Bao, Wenxuan Tong, Hanghang He, Jingrui |
| author_facet | He, Xinrui Li, Ting-Wei Wei, Tianxin Ning, Xuying He, Xinyu Bao, Wenxuan Tong, Hanghang He, Jingrui |
| contents | Federated cross-domain recommendation (Federated CDR) aims to collaboratively learn personalized recommendation models across heterogeneous domains while preserving data privacy. Recently, large language model (LLM)-based recommendation models have demonstrated impressive performance by leveraging LLMs' strong reasoning capabilities and broad knowledge. However, adopting LLM-based recommendation models in Federated CDR scenarios introduces new challenges. First, there exists a risk of overfitting with domain-specific local adapters. The magnitudes of locally optimized parameter updates often vary across domains, causing biased aggregation and overfitting toward domain-specific distributions. Second, unlike traditional recommendation models (e.g., collaborative filtering, bipartite graph-based methods) that learn explicit and comparable user/item representations, LLMs encode knowledge implicitly through autoregressive text generation training. This poses additional challenges for effectively measuring the cross-domain similarities under heterogeneity. To address these challenges, we propose an LLM-based framework for federated cross-domain recommendation, FeDecider. Specifically, FeDecider tackles the challenge of scale-specific noise by disentangling each client's low-rank updates and sharing only their directional components. To handle the need for flexible and effective integration, each client further learns personalized weights that achieve the data-aware integration of updates from other domains. Extensive experiments across diverse datasets validate the effectiveness of our proposed FeDecider. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16034 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FeDecider: An LLM-Based Framework for Federated Cross-Domain Recommendation He, Xinrui Li, Ting-Wei Wei, Tianxin Ning, Xuying He, Xinyu Bao, Wenxuan Tong, Hanghang He, Jingrui Information Retrieval Federated cross-domain recommendation (Federated CDR) aims to collaboratively learn personalized recommendation models across heterogeneous domains while preserving data privacy. Recently, large language model (LLM)-based recommendation models have demonstrated impressive performance by leveraging LLMs' strong reasoning capabilities and broad knowledge. However, adopting LLM-based recommendation models in Federated CDR scenarios introduces new challenges. First, there exists a risk of overfitting with domain-specific local adapters. The magnitudes of locally optimized parameter updates often vary across domains, causing biased aggregation and overfitting toward domain-specific distributions. Second, unlike traditional recommendation models (e.g., collaborative filtering, bipartite graph-based methods) that learn explicit and comparable user/item representations, LLMs encode knowledge implicitly through autoregressive text generation training. This poses additional challenges for effectively measuring the cross-domain similarities under heterogeneity. To address these challenges, we propose an LLM-based framework for federated cross-domain recommendation, FeDecider. Specifically, FeDecider tackles the challenge of scale-specific noise by disentangling each client's low-rank updates and sharing only their directional components. To handle the need for flexible and effective integration, each client further learns personalized weights that achieve the data-aware integration of updates from other domains. Extensive experiments across diverse datasets validate the effectiveness of our proposed FeDecider. |
| title | FeDecider: An LLM-Based Framework for Federated Cross-Domain Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2602.16034 |