mlsanityData to 7 Oct 2026

Low-pass Personalized Subgraph Federated Recommendation

arXiv 2603.20338 ↗First posted 20 Mar 2026cs.IR cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Recommender Systems (FRS) preserve privacy by training decentralized models on client-specific user-item subgraphs without sharing raw data. However, FRS faces a unique challenge: subgraph structural imbalance, where drastic variations in subgraph scale (user/item counts) and connectivity (item degree) misalign client representations, making it challenging to train a robust model that respects each client's unique structural characteristics. To address this, we propose a Low-pass Personalized Subgraph Federated recommender system (LPSFed). LPSFed leverages graph Fourier transforms and low-pass spectral filtering to extract low-frequency structural signals that remain stable across subgraphs of varying size and degree, allowing robust personalized parameter updates guided by similarity to a neutral structural anchor. Additionally, we leverage a localized popularity bias-aware margin that captures item-degree imbalance within each subgraph and incorporates it into a personalized bias correction term to mitigate recommendation bias. Supported by theoretical analysis and validated on five real-world datasets, LPSFed achieves superior recommendation accuracy and enhances model robustness.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 65 references that are in the map. First posted on arXiv 20 Mar 2026.

Builds on

44 of 65 references.

References · 44

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  3. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  4. 2016An overview of gradient descent optimization algorithmscited by 1,021
  5. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  6. 2019Neural Graph Collaborative Filteringcited by 660
  7. 2019Federated Learning with Personalization Layerscited by 533
  8. 2015An Introduction to Matrix Concentration Inequalitiescited by 391
  9. 2019Fair Resource Allocation in Federated Learningcited by 389
  10. 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 260
  11. 2020Federated Visual Classification with Real-World Data Distributioncited by 126
  12. 2020Disentangled Graph Collaborative Filteringcited by 118
32 more
  1. 2017How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utilitycited by 116
  2. 2019Secure Federated Matrix Factorizationcited by 102
  3. 2021FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendationcited by 97
  4. 2022KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systemscited by 94
  5. 2020Feedback Loop and Bias Amplification in Recommender Systemscited by 89
  6. 2019Managing Popularity Bias in Recommender Systems with Personalized Re-rankingcited by 81
  7. 2017Causal Embeddings for Recommendationcited by 79
  8. 2019Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedbackcited by 79
  9. 2022Towards Representation Alignment and Uniformity in Collaborative Filteringcited by 57
  10. 2022Personalized Subgraph Federated Learningcited by 54
  11. 2022Graph Filters for Signal Processing and Machine Learning on Graphscited by 53
  12. 2024FedGTA: Topology-aware Averaging for Federated Graph Learningcited by 44
  13. 2023A Survey on Popularity Bias in Recommender Systemscited by 42
  14. 2020Graph Convolutional Network for Recommendation with Low-pass Collaborative Filterscited by 32
  15. 2022Incorporating Bias-aware Margins into Contrastive Loss for Collaborative Filteringcited by 29
  16. 2023Personalized Graph Signal Processing for Collaborative Filteringcited by 29
  17. 2022LightFR: Lightweight Federated Recommendation with Privacy-preserving Matrix Factorizationcited by 26
  18. 2020A User Guide to Low-Pass Graph Signal Processing and its Applicationscited by 25
  19. 2023Semi-decentralized Federated Ego Graph Learning for Recommendationcited by 22
  20. 2024How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspectivecited by 21
  21. 2023Dual Personalization on Federated Recommendationcited by 19
  22. 2023Federated Heterogeneous Graph Neural Network for Privacy-preserving Recommendationcited by 18
  23. 2023No prejudice! Fair Federated Graph Neural Networks for Personalized Recommendationcited by 18
  24. 2024FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preferencecited by 16
  25. 2024Federated Graph Learning with Structure Proxy Alignmentcited by 14
  26. 2023Federated Learning over Coupled Graphscited by 12
  27. 2023Federated Recommendation with Additive Personalizationcited by 9
  28. 2024General Debiasing for Graph-based Collaborative Filtering via Adversarial Graph Dropoutcited by 7
  29. 2025S2FGL: Spatial Spectral Federated Graph Learningcited by 7
  30. 2025Homophily Heterogeneity Matters in Graph Federated Learning: A Spectrum Sharing and Complementing Perspectivecited by 4
  31. 2025Curriculum Guided Personalized Subgraph Federated Learningcited by 4
  32. 2025Federated Recommender System with Data Valuation for E-commerce Platformcited by 2

Built on by

Not cited yet.