Learning to Collaborate via Structures: Cluster-Guided Item Alignment for Federated Recommendation

• URL: http://arxiv.org/abs/2602.21957v1
• Date: Wed, 25 Feb 2026 14:39:47 GMT
• Title: Learning to Collaborate via Structures: Cluster-Guided Item Alignment for Federated Recommendation
• Abstract summary: Federated recommendation facilitates collaborative model training across distributed clients while keeping sensitive user interaction data local.<n>We propose Cluster-Guided FedRec framework (CGFedRec), a framework that transforms uploaded embeddings into compact cluster labels.
• Score: 20.406834399432544
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Federated recommendation facilitates collaborative model training across distributed clients while keeping sensitive user interaction data local. Conventional approaches typically rely on synchronizing high-dimensional item representations between the server and clients. This paradigm implicitly assumes that precise geometric alignment of embedding coordinates is necessary for collaboration across clients. We posit that establishing relative semantic relationships among items is more effective than enforcing shared representations. Specifically, global semantic relations serve as structural constraints for items. Within these constraints, the framework allows item representations to vary locally on each client, which flexibility enables the model to capture fine-grained user personalization while maintaining global consistency. To this end, we propose Cluster-Guided FedRec framework (CGFedRec), a framework that transforms uploaded embeddings into compact cluster labels. In this framework, the server functions as a global structure discoverer to learn item clusters and distributes only the resulting labels. This mechanism explicitly cuts off the downstream transmission of item embeddings, relieving clients from maintaining global shared item embeddings. Consequently, CGFedRec achieves the effective injection of global collaborative signals into local item representations without transmitting full embeddings. Extensive experiments demonstrate that our approach significantly improves communication efficiency while maintaining superior recommendation accuracy across multiple datasets.

Related papers

• FedHUR: Learning Hierarchical Utility-Guided Client Relations for Personalized Federated Recommendation [44.13013639783267]
  Federated recommendation enables collaborative model training while keeping user interaction data on local clients.<n>FedHUR is a framework for learning hierarchical utility-guided client relations.<n>Experiments on five real-world datasets show that FedHUR consistently outperforms existing federated recommendation baselines.
  arXiv  Detail & Related papers  (2026-09-10T14:42:24Z)
• FedHarmony: Harmonizing Heterogeneous Label Correlations in Federated Multi-Label Learning [76.62016339908384]
  We propose FedHarmony, a framework that harmonizes heterogeneous label correlations across clients.<n>During aggregation, FedHarmony evaluates each client by both data size and correlation quality, assigning weights accordingly.<n>Experiments on real-world federated multi-label datasets show that FedHarmony consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-04-30T15:42:17Z)
• One-Shot Hierarchical Federated Clustering [51.490181220883905]
  This paper introduces an efficient one-shot hierarchical Federated Clustering framework.<n>It performs client-end distribution exploration and server-end distribution aggregation.<n>It turns out that the complex cluster distributions across clients can be efficiently explored.
  arXiv  Detail & Related papers  (2026-01-10T02:58:33Z)
• Federated Multi-Task Clustering [44.73672172790804]
  This paper proposes a novel framework named Federated Multi-Task Clustering (i.e.,FMTC)<n>It is composed of two main components: client-side personalized clustering module and server-side tensorial correlation module.<n>We derive an efficient, privacy-preserving distributed algorithm based on the Alternating Direction Method of Multipliers.
  arXiv  Detail & Related papers  (2025-12-28T12:02:32Z)
• Towards Federated Clustering: A Client-wise Private Graph Aggregation Framework [57.04850867402913]
  Federated clustering addresses the challenge of extracting patterns from decentralized, unlabeled data.<n>We propose Structural Privacy-Preserving Federated Graph Clustering (SPP-FGC), a novel algorithm that innovatively leverages local structural graphs as the primary medium for privacy-preserving knowledge sharing.<n>Our framework achieves state-of-the-art performance, improving clustering accuracy by up to 10% (NMI) over federated baselines while maintaining provable privacy guarantees.
  arXiv  Detail & Related papers  (2025-11-14T03:05:22Z)
• Learning to Collaborate Over Graphs: A Selective Federated Multi-Task Learning Approach [34.756818299081736]
  We present a novel multi-task learning method that leverages cross-client similarity to enable personalized learning for each client.<n>We propose a communication-efficient scheme that introduces a feature anchor, a compact vector representation that summarizes the features learned from the client's local classes.<n>In addition, the clients share the classification heads, a lightweight linear layer, and perform a graph-based regularization to enable collaboration among clients.
  arXiv  Detail & Related papers  (2025-06-11T18:39:18Z)
• Federated Continual 3D Segmentation With Single-round Communication [8.95113819926435]
  Federated learning seeks to foster collaboration among distributed clients while preserving the privacy of their local data.<n>In such a dynamic federated analysis setup, the conventional federated communication strategy of model aggregation per communication round is suboptimal.<n>In this paper, we propose a federated continual learning strategy that employs a one-time model aggregation at the server through multi-model distillation.
  arXiv  Detail & Related papers  (2025-03-19T16:56:34Z)
• Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting [10.061328213032088]
  Federated Class-Incremental Learning (FCIL) refers to a scenario where a dynamically changing number of clients collaboratively learn an ever-increasing number of incoming tasks.<n>We develop a mathematical framework for FCIL that formulates local and global forgetting.<n>We propose an approach called Hybrid Rehearsal which utilizes latent exemplars and data-free techniques to address local and global forgetting.
  arXiv  Detail & Related papers  (2025-01-26T01:08:01Z)
• Co-clustering for Federated Recommender System [33.70723179405055]
  Federated Recommender System (FRS) offers a solution that strikes a balance between providing high-quality recommendations and preserving user privacy. The presence of statistical heterogeneity in FRS, commonly observed due to personalized decision-making patterns, can pose challenges. We propose CoFedRec, a novel Co-clustering Federated Recommendation mechanism.
  arXiv  Detail & Related papers  (2024-11-03T21:32:07Z)
• Federated Learning with Only Positive Labels by Exploring Label Correlations [78.59613150221597]
  Federated learning aims to collaboratively learn a model by using the data from multiple users under privacy constraints. In this paper, we study the multi-label classification problem under the federated learning setting. We propose a novel and generic method termed Federated Averaging by exploring Label Correlations (FedALC)
  arXiv  Detail & Related papers  (2024-04-24T02:22:50Z)
• APGL4SR: A Generic Framework with Adaptive and Personalized Global Collaborative Information in Sequential Recommendation [86.29366168836141]
  We propose a graph-driven framework, named Adaptive and Personalized Graph Learning for Sequential Recommendation (APGL4SR) APGL4SR incorporates adaptive and personalized global collaborative information into sequential recommendation systems. As a generic framework, APGL4SR can outperform other baselines with significant margins.
  arXiv  Detail & Related papers  (2023-11-06T01:33:24Z)
• Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces [59.33965805898736]
  Clustered learning has been shown to produce promising results by grouping clients into clusters. Existing FL algorithms are essentially trying to group clients together with similar distributions. Prior FL algorithms attempt similarities indirectly during training.
  arXiv  Detail & Related papers  (2022-09-21T17:37:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.