mlsanityData to 14 Oct 2026

Personalized Federated Learning for Spatio-Temporal Forecasting: A Dual Semantic Alignment-Based Contrastive Approach

arXiv 2404.03702 ↗First posted 4 Apr 2024cs.LG cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

The existing federated learning (FL) methods for spatio-temporal forecasting fail to capture the inherent spatio-temporal heterogeneity, which calls for personalized FL (PFL) methods to model the spatio-temporally variant patterns. While contrastive learning approach is promising in addressing spatio-temporal heterogeneity, the existing methods are noneffective in determining negative pairs and can hardly apply to PFL paradigm. To tackle this limitation, we propose a novel PFL method, named Federated dUal sEmantic aLignment-based contraStive learning (FUELS), which can adaptively align positive and negative pairs based on semantic similarity, thereby injecting precise spatio-temporal heterogeneity into the latent representation space by auxiliary contrastive tasks. From temporal perspective, a hard negative filtering module is introduced to dynamically align heterogeneous temporal representations for the supplemented intra-client contrastive task. From spatial perspective, we design lightweight-but-efficient prototypes as client-level semantic representations, based on which the server evaluates spatial similarity and yields client-customized global prototypes for the supplemented inter-client contrastive task. Extensive experiments demonstrate that FUELS outperforms state-of-the-art methods, with communication cost decreasing by around 94%.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 38 of its 51 references that are in the map. First posted on arXiv 4 Apr 2024.

Builds on

38 of 51 references.

References · 38

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  4. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  7. 2021Model-Contrastive Federated Learningcited by 766
  8. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  9. 2017Federated Multi-Task Learningcited by 672
  10. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  11. 2019Federated Learning with Personalization Layerscited by 541
  12. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 541
26 more
  1. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  2. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  3. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 471
  4. 2021Towards Personalized Federated Learningcited by 464
  5. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
  6. 2020Understanding the Behaviour of Contrastive Losscited by 398
  7. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 383
  8. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 325
  9. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 213
  10. 2022CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecastingcited by 144
  11. 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 142
  12. 2023Stochastic Controlled Averaging for Federated Learning with Communication Compressioncited by 101
  13. 2023Multimodal Federated Learning via Contrastive Representation Ensemblecited by 86
  14. 2020Privacy-preserving Traffic Flow Prediction: A Federated Learning Approachcited by 83
  15. 2021FedProc: Prototypical Contrastive Federated Learning on Non-IID datacited by 81
  16. 2022Spatio-Temporal Self-Supervised Learning for Traffic Flow Predictioncited by 77
  17. 2021Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modelingcited by 69
  18. 2020Federated learning with class imbalance reductioncited by 52
  19. 2023Efficient Personalized Federated Learning via Sparse Model-Adaptationcited by 38
  20. 2021When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting?cited by 36
  21. 2019Federated User Representation Learningcited by 32
  22. 2021Privacy-preserving Spatiotemporal Scenario Generation of Renewable Energies: A Federated Deep Generative Learning Approachcited by 22
  23. 2021Dual Attention-Based Federated Learning for Wireless Traffic Predictioncited by 18
  24. 2021FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systemscited by 16
  25. 2022Federated Learning for 5G Base Station Traffic Forecastingcited by 15
  26. 2023Online Spatio-Temporal Correlation-Based Federated Learning for Traffic Flow Forecastingcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 6.

8 papers.

  1. 2025Out-of-Distribution Generalization in Time Series: A Surveycited by 16
  2. 2026FedDis: A Causal Disentanglement Framework for Federated Traffic Predictioncited by 2
  3. 2024CurvFed: Curvature-Aligned Federated Learning for Fairness without Demographicscited by 1
  4. 2026Causality-inspired Federated Learning for Dynamic Spatio-Temporal Graphscited by 1
  5. 2026Discrete Prototypical Memories for Federated Time Series Foundation Modelscited by 1
  6. 2026CoRe-Fed: Bridging Collaborative and Representation Fairness via Federated Embedding Distillationcited by 0
  7. 2026Every Client Is an Environment: Federated De-confounding for Spatio-Temporal Forecastingcited by 0
  8. 2026F2STNet: Fair and Federated Spectral-Temporal Modeling for Graph Forecastingcited by 0