A Model-agnostic Strategy to Mitigate Embedding Degradation in Personalized Federated Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shen, Jiakui, Mi, Yunqi, Zhao, Guoshuai, Shen, Jialie, Qian, Xueming
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916920846974976
author Shen, Jiakui
Mi, Yunqi
Zhao, Guoshuai
Shen, Jialie
Qian, Xueming
author_facet Shen, Jiakui
Mi, Yunqi
Zhao, Guoshuai
Shen, Jialie
Qian, Xueming
contents Centralized recommender systems encounter privacy leakage due to the need to collect user behavior and other private data. Hence, federated recommender systems (FedRec) have become a promising approach with an aggregated global model on the server. However, this distributed training paradigm suffers from embedding degradation caused by suboptimal personalization and dimensional collapse, due to the existence of sparse interactions and heterogeneous preferences. To this end, we propose a novel model-agnostic strategy for FedRec to strengthen the personalized embedding utility, which is called Personalized Local-Global Collaboration (PLGC). It is the first research in federated recommendation to alleviate the dimensional collapse issue. Particularly, we incorporate the frozen global item embedding table into local devices. Based on a Neural Tangent Kernel strategy that dynamically balances local and global information, PLGC optimizes personalized representations during forward inference, ultimately converging to user-specific preferences. Additionally, PLGC carries on a contrastive objective function to reduce embedding redundancy by dissolving dependencies between dimensions, thereby improving the backward representation learning process. We introduce PLGC as a model-agnostic personalized training strategy for federated recommendations that can be applied to existing baselines to alleviate embedding degradation. Extensive experiments on five real-world datasets have demonstrated the effectiveness and adaptability of PLGC, which outperforms various baseline algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19591
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Model-agnostic Strategy to Mitigate Embedding Degradation in Personalized Federated Recommendation
Shen, Jiakui
Mi, Yunqi
Zhao, Guoshuai
Shen, Jialie
Qian, Xueming
Information Retrieval
Distributed, Parallel, and Cluster Computing
Centralized recommender systems encounter privacy leakage due to the need to collect user behavior and other private data. Hence, federated recommender systems (FedRec) have become a promising approach with an aggregated global model on the server. However, this distributed training paradigm suffers from embedding degradation caused by suboptimal personalization and dimensional collapse, due to the existence of sparse interactions and heterogeneous preferences. To this end, we propose a novel model-agnostic strategy for FedRec to strengthen the personalized embedding utility, which is called Personalized Local-Global Collaboration (PLGC). It is the first research in federated recommendation to alleviate the dimensional collapse issue. Particularly, we incorporate the frozen global item embedding table into local devices. Based on a Neural Tangent Kernel strategy that dynamically balances local and global information, PLGC optimizes personalized representations during forward inference, ultimately converging to user-specific preferences. Additionally, PLGC carries on a contrastive objective function to reduce embedding redundancy by dissolving dependencies between dimensions, thereby improving the backward representation learning process. We introduce PLGC as a model-agnostic personalized training strategy for federated recommendations that can be applied to existing baselines to alleviate embedding degradation. Extensive experiments on five real-world datasets have demonstrated the effectiveness and adaptability of PLGC, which outperforms various baseline algorithms.
title A Model-agnostic Strategy to Mitigate Embedding Degradation in Personalized Federated Recommendation
topic Information Retrieval
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2508.19591