# Optimizing Federated Graph Learning with Inherent Structural Knowledge and Dual-Densely Connected GNNs

arXiv: https://arxiv.org/abs/2408.11662 · HTML: https://mlsanity.com/paper/2408.11662/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 21 Aug 2024.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [TUDataset: A collection of benchmark datasets for learning with graphs](https://mlsanity.com/paper/2007.08663/) (2020)
- [Graph Neural Networks with Learnable Structural and Positional Representations](https://mlsanity.com/paper/2110.07875/) (2021)
- [Relational Pooling for Graph Representations](https://mlsanity.com/paper/1903.02541/) (2019)
- [Fake News Detection on Social Media using Geometric Deep Learning](https://mlsanity.com/paper/1902.06673/) (2019)
- [Federated Graph Classification over Non-IID Graphs](https://mlsanity.com/paper/2106.13423/) (2021)
- [Federated Learning on Non-IID Graphs via Structural Knowledge Sharing](https://mlsanity.com/paper/2211.13009/) (2022)
- [GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphs](https://mlsanity.com/paper/2012.04187/) (2020)
- [On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs](https://mlsanity.com/paper/2107.01495/) (2021)
- [Federated Graph Learning -- A Position Paper](https://mlsanity.com/paper/2105.11099/) (2021)
- [Evaluating Deep Graph Neural Networks](https://mlsanity.com/paper/2108.00955/) (2021)
- [A Survey on Graph Classification and Link Prediction based on GNN](https://mlsanity.com/paper/2307.00865/) (2023)
- [Lumos: Heterogeneity-aware Federated Graph Learning over Decentralized Devices](https://mlsanity.com/paper/2303.00492/) (2023)
- [The Impact of Global Structural Information in Graph Neural Networks Applications](https://mlsanity.com/paper/2006.03814/) (2020)
- [Can strong structural encoding reduce the importance of Message Passing?](https://mlsanity.com/paper/2310.15197/) (2023)
- [Directed Graph Attention Neural Network Utilizing 3D Coordinates for Molecular Property Prediction](https://mlsanity.com/paper/2012.00404/) (2020)

## Abstract (arXiv)

Federated Graph Learning (FGL) is an emerging technology that enables clients to collaboratively train powerful Graph Neural Networks (GNNs) in a distributed manner without exposing their private data. Nevertheless, FGL still faces the challenge of the severe non-Independent and Identically Distributed (non-IID) nature of graphs, which possess diverse node and edge structures, especially across varied domains. Thus, exploring the knowledge inherent in these structures becomes significantly crucial. Existing methods, however, either overlook the inherent structural knowledge in graph data or capture it at the cost of significantly increased resource demands (e.g., FLOPs and communication bandwidth), which can be detrimental to distributed paradigms. Inspired by this, we propose FedDense, a novel FGL framework that optimizes the utilization efficiency of inherent structural knowledge. To better acquire knowledge of diverse and underexploited structures, FedDense first explicitly encodes the structural knowledge inherent within graph data itself alongside node features. Besides, FedDense introduces a Dual-Densely Connected (DDC) GNN architecture that exploits the multi-scale (i.e., one-hop to multi-hop) feature and structure insights embedded in the aggregated feature maps at each layer. In addition to the exploitation of inherent structures, we consider resource limitations in FGL, devising exceedingly narrow layers atop the DDC architecture and adopting a selective parameter sharing strategy to reduce resource costs substantially. We conduct extensive experiments using 15 datasets across 4 different domains, demonstrating that FedDense consistently surpasses baselines by a large margin in training performance, while demanding minimal resources.