FlatLand: Personalized Graph Federated Learning via Tailored Lorentz Space
Not on the map. Why?
Abstract (arXiv)
Federated learning enables privacy-preserving collaborative training, but highly heterogeneous client data remain challenging, especially in graph federated learning where clients possess structurally diverse graphs. Existing personalized federated learning (PFL) methods ignore the intrinsic geometric properties of diverse graph structures. We propose FlatLand, a novel personalized federated learning method that embeds different clients' data in tailored Lorentz space of hyperbolic geometry. Our key insight is that hyperbolic geometry naturally accommodates the intrinsic negative curvature prevalent in real-world graphs, while the time-like dimension in Lorentz space provides a principled way to encode client-specific heterogeneity. We develop a parameter decoupling strategy that separates heterogeneous information (captured in time-like parameters) from common knowledge (preserved in space-like parameters), enabling direct aggregation without requiring client similarity estimation and extra calculation modules. Empirical results on diverse federated graph learning tasks demonstrate that FlatLand achieves superior performance, particularly in low-dimensional settings.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 47 of its 69 references that are in the map. First posted on arXiv 21 Aug 2026.
Builds on
47 of 69 references.
References · 47
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2019Advances and Open Problems in Federated Learningcited by 3,046
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
- 2020Adaptive Federated Optimizationcited by 1,046
- 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
- 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
- 2020Personalized Federated Learning with Moreau Envelopescited by 618
35 more
- 2019Federated Learning with Personalization Layerscited by 541
- 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
- 2021Towards Personalized Federated Learningcited by 464
- 2019Hyperbolic Graph Convolutional Neural Networkscited by 402
- 2020Adaptive Personalized Federated Learningcited by 358
- 2020Three Approaches for Personalization with Applications to Federated Learningcited by 325
- 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 283
- 2019Improving Federated Learning Personalization via Model Agnostic Meta Learningcited by 269
- 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 265
- 2019Hyperbolic Image Embeddingscited by 221
- 2020Federated Learning of a Mixture of Global and Local Modelscited by 210
- 2020Personalized Federated Learning with First Order Model Optimizationcited by 201
- 2019Federated Evaluation of On-device Personalizationcited by 147
- 2021Hyperbolic Deep Neural Networks: A Surveycited by 139
- 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
- 2021Federated Graph Classification over Non-IID Graphscited by 114
- 2021Fully Hyperbolic Neural Networkscited by 108
- 2022Hyperbolic Image Segmentationcited by 102
- 2022Federated Learning on Non-IID Graphs via Structural Knowledge Sharingcited by 88
- 2025A Survey of Personalized Large Language Models: Progress and Future Directionscited by 71
- 2021Lorentzian Graph Convolutional Networkscited by 68
- 2022Personalized Subgraph Federated Learningcited by 54
- 2021Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learningcited by 53
- 2024FedGTA: Topology-aware Averaging for Federated Graph Learningcited by 44
- 2024Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Spacecited by 43
- 2022Hyperbolic Graph Neural Networks: A Review of Methods and Applicationscited by 40
- 2024AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneitycited by 25
- 2022Enhancing Hyperbolic Graph Embeddings via Contrastive Learningcited by 20
- 2023Curvature Filtrations for Graph Generative Model Evaluationcited by 19
- 2025Position: Beyond Euclidean -- Foundation Models Should Embrace Non-Euclidean Geometriescited by 18
- 2023Understanding and Mitigating Hyperbolic Dimensional Collapse in Graph Contrastive Learningcited by 9
- 2023HyperFed: Hyperbolic Prototypes Exploration with Consistent Aggregation for Non-IID Data in Federated Learningcited by 8
- 2023Federated Learning with Manifold Regularization and Normalized Update Reaggregationcited by 8
- 2024HC-GLAD: Dual Hyperbolic Contrastive Learning for Unsupervised Graph-Level Anomaly Detectioncited by 5
- 2024Contrastive Sequential Interaction Network Learning on Co-Evolving Riemannian Spacescited by 3
Built on by
Citing papers per year: 2026: 2.
2 papers.