SGFusion: Stochastic Geographic Gradient Fusion in Federated Learning

• URL: http://arxiv.org/abs/2510.23455v3
• Date: Wed, 29 Oct 2025 14:29:54 GMT
• Title: SGFusion: Stochastic Geographic Gradient Fusion in Federated Learning
• Abstract summary: Geographic Gradient Fusion (SGFusion) is a novel training algorithm to leverage the geographic information of mobile users in Federated Learning (FL)<n> SGFusion maps the data collected by mobile devices onto geographical zones and trains one FL model per zone, which adapts well to the data and behaviors of users in that zone.
• Score: 9.880571400081669
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper proposes Stochastic Geographic Gradient Fusion (SGFusion), a novel training algorithm to leverage the geographic information of mobile users in Federated Learning (FL). SGFusion maps the data collected by mobile devices onto geographical zones and trains one FL model per zone, which adapts well to the data and behaviors of users in that zone. SGFusion models the local data-based correlation among geographical zones as a hierarchical random graph (HRG) optimized by Markov Chain Monte Carlo sampling. At each training step, every zone fuses its local gradient with gradients derived from a small set of other zones sampled from the HRG. This approach enables knowledge fusion and sharing among geographical zones in a probabilistic and stochastic gradient fusion process with self-attention weights, such that "more similar" zones have "higher probabilities" of sharing gradients with "larger attention weights." SGFusion remarkably improves model utility without introducing undue computational cost. Extensive theoretical and empirical results using a heart-rate prediction dataset collected across 6 countries show that models trained with SGFusion converge with upper-bounded expected errors and significantly improve utility in all countries compared to existing approaches without notable cost in system scalability.

Related papers

• CuBAS: Information Geometric Curvature-Based Adaptive Sampling for Supervised Classification [52.452902154360565]
  CuBAS is an information-geometric framework for adaptive data selection in supervised classification.<n>A labeled dataset can be viewed as a statistical manifold, on which local curvature, estimated via the ratio of second to first-order observed Fisher information, faithfully encodes the geometric complexity of the data distribution.
  arXiv  Detail & Related papers  (2026-07-03T09:36:02Z)
• Revealing Geography-Driven Signals in Zone-Level Claim Frequency Models: An Empirical Study using Environmental and Visual Predictors [1.5484595752241122]
  Geographic context is often consider relevant to motor insurance risk, yet public actuarial datasets provide limited location identifiers.<n>This study examines how geographic information from alternative data sources can be incorporated into actuarial models for Motor Third Party Liability (MTPL) claim prediction.
  arXiv  Detail & Related papers  (2026-04-23T17:44:52Z)
• Fusion and Grouping Strategies in Deep Learning for Local Climate Zone Classification of Multimodal Remote Sensing Data [1.3607388598209322]
  Local Climate Zones (LCZs) give a zoning map to study urban structures and land use.<n>Data fusion is significant for improving accuracy owing to the data complexity.<n>This study analyzes different fusion strategies in the multi-class LCZ classification models.
  arXiv  Detail & Related papers  (2026-03-04T19:47:13Z)
• M-SGWR: Multiscale Similarity and Geographically Weighted Regression [0.41942958779358674]
  M-SGWR characterizes spatial interaction across two dimensions: geographic proximity and attribute (variable) similarity.<n>We show that M-SGWR consistently outperforms GWR, SGWR, and MGWR across all goodness-of-fit metrics.
  arXiv  Detail & Related papers  (2026-01-27T18:55:12Z)
• Population synthesis with geographic coordinates [1.6419687521433917]
  It is increasingly important to generate synthetic populations with explicit coordinates rather than coarse geographic areas.<n>We propose a population synthesis algorithm that maps spatial coordinates into a more regular latent space.<n>We demonstrate the method by generating synthetic homes with the same statistical properties of real homes in 121 datasets.
  arXiv  Detail & Related papers  (2025-10-08T13:36:13Z)
• PlaceFM: A Training-free Geospatial Foundation Model of Places using Large-Scale Point of Interest Data [0.5735035463793009]
  PlaceFM captures place representations through a training-free, clustering-based approach.<n>placeFM summarizes the entire point of interest graph constructed from U.S. Foursquare data.<n>placeFM produces general-purpose region embeddings while automatically identifying places of interest.<n>placeFM achieves up to a 100x speedup in generating region-level representations on large-scale POI graphs.
  arXiv  Detail & Related papers  (2025-06-25T15:10:31Z)
• TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation [65.74990259650984]
  We introduce TerraFM, a scalable self-supervised learning model that leverages globally distributed Sentinel-1 and Sentinel-2 imagery.<n>Our training strategy integrates local-global contrastive learning and introduces a dual-centering mechanism.<n>TerraFM achieves strong generalization on both classification and segmentation tasks, outperforming prior models on GEO-Bench and Copernicus-Bench.
  arXiv  Detail & Related papers  (2025-06-06T17:59:50Z)
• An Interpretable Implicit-Based Approach for Modeling Local Spatial Effects: A Case Study of Global Gross Primary Productivity [9.352810748734157]
  In Earth sciences, unobserved factors exhibit non-stationary distributions, causing the relationships between features and targets to display spatial heterogeneity.<n>In geographic machine learning tasks, conventional statistical learning methods often struggle to capture spatial heterogeneity.<n>We propose a novel perspective - that is, simultaneously modeling common features across different locations alongside spatial differences using deep neural networks.
  arXiv  Detail & Related papers  (2025-02-10T05:44:54Z)
• Space-aware Socioeconomic Indicator Inference with Heterogeneous Graphs [46.52719756897067]
  We present GeoHG, the first space-aware socioeconomic indicator inference method that utilizes a heterogeneous graph-based structure to represent geospace for non-continuous inference.
  arXiv  Detail & Related papers  (2024-05-23T03:19:02Z)
• An Aggregation-Free Federated Learning for Tackling Data Heterogeneity [50.44021981013037]
  Federated Learning (FL) relies on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework, where clients update local models based on a global model aggregated by the server from the previous training round. We introduce FedAF, a novel aggregation-free FL algorithm.
  arXiv  Detail & Related papers  (2024-04-29T05:55:23Z)
• Learning Regionalization using Accurate Spatial Cost Gradients within a Differentiable High-Resolution Hydrological Model: Application to the French Mediterranean Region [0.18139022013189662]
  Estimating distributed hydrological parameters in ungauged catchments poses a challenging regionalization problem. This paper introduces a Hybrid Assimilation and Regionalization (HDA-PR) approach incorporating learnable regionalization mappings. Results highlight a strong regionalization of HDA-PR especially in the most challenging upstream-to-downstream extrapolation scenario.
  arXiv  Detail & Related papers  (2023-08-02T07:23:50Z)
• Federated Stochastic Gradient Descent Begets Self-Induced Momentum [151.4322255230084]
  Federated learning (FL) is an emerging machine learning method that can be applied in mobile edge systems. We show that running to the gradient descent (SGD) in such a setting can be viewed as adding a momentum-like term to the global aggregation process.
  arXiv  Detail & Related papers  (2022-02-17T02:01:37Z)
• Multi-Level Graph Convolutional Network with Automatic Graph Learning for Hyperspectral Image Classification [63.56018768401328]
  We propose a Multi-level Graph Convolutional Network (GCN) with Automatic Graph Learning method (MGCN-AGL) for HSI classification. By employing attention mechanism to characterize the importance among spatially neighboring regions, the most relevant information can be adaptively incorporated to make decisions. Our MGCN-AGL encodes the long range dependencies among image regions based on the expressive representations that have been produced at local level.
  arXiv  Detail & Related papers  (2020-09-19T09:26:20Z)
• Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning [85.6386289476598]
  We develop a novel adversarial graph representation adaptation (AGRA) framework for cross-domain holistic-local feature co-adaptation. We conduct extensive and fair evaluations on several popular benchmarks and show that the proposed AGRA framework outperforms previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-08-03T15:00:31Z)
• Adversarial Graph Representation Adaptation for Cross-Domain Facial Expression Recognition [86.25926461936412]
  We propose a novel Adrialversa Graph Representation Adaptation (AGRA) framework that unifies graph representation propagation with adversarial learning for cross-domain holistic-local feature co-adaptation. We conduct extensive and fair experiments on several popular benchmarks and show that the proposed AGRA framework achieves superior performance over previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-08-03T13:27:24Z)

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.