# Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling

arXiv: https://arxiv.org/abs/2106.05223 · HTML: https://mlsanity.com/paper/2106.05223/

## Key facts

- Cited by 69 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 9 Jun 2021.

## Builds on (most cited first, 25 of 25)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Federated Multi-Task Learning](https://mlsanity.com/paper/1705.10467/) (2017)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [Neural Relational Inference for Interacting Systems](https://mlsanity.com/paper/1802.04687/) (2018)
- [Think Locally, Act Globally: Federated Learning with Local and Global Representations](https://mlsanity.com/paper/2001.01523/) (2020)
- [Position-aware Graph Neural Networks](https://mlsanity.com/paper/1906.04817/) (2019)
- [Adaptive Sampling Towards Fast Graph Representation Learning](https://mlsanity.com/paper/1809.05343/) (2018)
- [What Can Neural Networks Reason About?](https://mlsanity.com/paper/1905.13211/) (2019)
- [Non-convex Optimization for Machine Learning](https://mlsanity.com/paper/1712.07897/) (2017)
- [Forecasting Sequential Data using Consistent Koopman Autoencoders](https://mlsanity.com/paper/2003.02236/) (2020)
- [Detailed comparison of communication efficiency of split learning and federated learning](https://mlsanity.com/paper/1909.09145/) (2019)
- [Simple, Efficient, and Neural Algorithms for Sparse Coding](https://mlsanity.com/paper/1503.00778/) (2015)
- [Towards Federated Graph Learning for Collaborative Financial Crimes Detection](https://mlsanity.com/paper/1909.12946/) (2019)
- [New Algorithms for Learning Incoherent and Overcomplete Dictionaries](https://mlsanity.com/paper/1308.6273/) (2013)
- [Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge](https://mlsanity.com/paper/2007.14513/) (2020)

## Built on by (most cited first, 30 of 69)

- [Federated Graph Classification over Non-IID Graphs](https://mlsanity.com/paper/2106.13423/) (2021)
- [Trustworthy Graph Neural Networks: Aspects, Methods and Trends](https://mlsanity.com/paper/2205.07424/) (2022)
- [Federated Learning on Non-IID Graphs via Structural Knowledge Sharing](https://mlsanity.com/paper/2211.13009/) (2022)
- [FedLab: A Flexible Federated Learning Framework](https://mlsanity.com/paper/2107.11621/) (2021)
- [Federated Graph Neural Networks: Overview, Techniques and Challenges](https://mlsanity.com/paper/2202.07256/) (2022)
- [GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation](https://mlsanity.com/paper/2203.00949/) (2022)
- [pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning](https://mlsanity.com/paper/2206.03655/) (2022)
- [Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI](https://mlsanity.com/paper/2111.06061/) (2021)
- [Efficient Personalized Federated Learning via Sparse Model-Adaptation](https://mlsanity.com/paper/2305.02776/) (2023)
- [FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networks](https://mlsanity.com/paper/2201.12433/) (2022)
- [On the Convergence of Zeroth-Order Federated Tuning for Large Language Models](https://mlsanity.com/paper/2402.05926/) (2024)
- [LightTR: A Lightweight Framework for Federated Trajectory Recovery](https://mlsanity.com/paper/2405.03409/) (2024)
- [Federated Cycling (FedCy): Semi-supervised Federated Learning of Surgical Phases](https://mlsanity.com/paper/2203.07345/) (2022)
- [Towards Private Learning on Decentralized Graphs with Local Differential Privacy](https://mlsanity.com/paper/2201.09398/) (2022)
- [STFL: A Temporal-Spatial Federated Learning Framework for Graph Neural Networks](https://mlsanity.com/paper/2111.06750/) (2021)
- [Federated Graph Machine Learning: A Survey of Concepts, Techniques, and Applications](https://mlsanity.com/paper/2207.11812/) (2022)
- [Federated Learning over Coupled Graphs](https://mlsanity.com/paper/2301.11099/) (2023)
- [GNN at the Edge: Cost-Efficient Graph Neural Network Processing over Distributed Edge Servers](https://mlsanity.com/paper/2210.17281/) (2022)
- [SecGNN: Privacy-Preserving Graph Neural Network Training and Inference as a Cloud Service](https://mlsanity.com/paper/2202.07835/) (2022)
- [FedGS: Federated Graph-based Sampling with Arbitrary Client Availability](https://mlsanity.com/paper/2211.13975/) (2022)
- [Spatial-Temporal Networks for Antibiogram Pattern Prediction](https://mlsanity.com/paper/2305.01761/) (2023)
- [FedWalk: Communication Efficient Federated Unsupervised Node Embedding with Differential Privacy](https://mlsanity.com/paper/2205.15896/) (2022)
- [Towards Fair Graph Federated Learning via Incentive Mechanisms](https://mlsanity.com/paper/2312.13306/) (2023)
- [Personalized Federated Learning for Spatio-Temporal Forecasting: A Dual Semantic Alignment-Based Contrastive Approach](https://mlsanity.com/paper/2404.03702/) (2024)
- [An Adaptive Federated Relevance Framework for Spatial Temporal Graph Learning](https://mlsanity.com/paper/2206.03420/) (2022)
- [Online Spatio-Temporal Correlation-Based Federated Learning for Traffic Flow Forecasting](https://mlsanity.com/paper/2302.08658/) (2023)
- [Advancements in Federated Learning: Models, Methods, and Privacy](https://mlsanity.com/paper/2302.11466/) (2023)
- [PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection](https://mlsanity.com/paper/2406.02318/) (2024)
- [A Comprehensive Data-centric Overview of Federated Graph Learning](https://mlsanity.com/paper/2507.16541/) (2025)
- [Distributed Learning over Networks with Graph-Attention-Based Personalization](https://mlsanity.com/paper/2305.13041/) (2023)

## Abstract (arXiv)

Vast amount of data generated from networks of sensors, wearables, and the Internet of Things (IoT) devices underscores the need for advanced modeling techniques that leverage the spatio-temporal structure of decentralized data due to the need for edge computation and licensing (data access) issues. While federated learning (FL) has emerged as a framework for model training without requiring direct data sharing and exchange, effectively modeling the complex spatio-temporal dependencies to improve forecasting capabilities still remains an open problem. On the other hand, state-of-the-art spatio-temporal forecasting models assume unfettered access to the data, neglecting constraints on data sharing. To bridge this gap, we propose a federated spatio-temporal model -- Cross-Node Federated Graph Neural Network (CNFGNN) -- which explicitly encodes the underlying graph structure using graph neural network (GNN)-based architecture under the constraint of cross-node federated learning, which requires that data in a network of nodes is generated locally on each node and remains decentralized. CNFGNN operates by disentangling the temporal dynamics modeling on devices and spatial dynamics on the server, utilizing alternating optimization to reduce the communication cost, facilitating computations on the edge devices. Experiments on the traffic flow forecasting task show that CNFGNN achieves the best forecasting performance in both transductive and inductive learning settings with no extra computation cost on edge devices, while incurring modest communication cost.