# Dissecting Federated-Graph Aggregation under Domain Shift: Importance-Aware Aggregation via Empirical Analysis

arXiv: https://arxiv.org/abs/2509.18171 · HTML: https://mlsanity.com/paper/2509.18171/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## Builds on (most cited first, 18 of 18)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [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)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [Subgraph Federated Learning with Missing Neighbor Generation](https://mlsanity.com/paper/2106.13430/) (2021)
- [FedGTA: Topology-aware Averaging for Federated Graph Learning](https://mlsanity.com/paper/2401.11755/) (2024)
- [Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs](https://mlsanity.com/paper/2212.09034/) (2022)
- [FedGraph: Federated Graph Learning with Intelligent Sampling](https://mlsanity.com/paper/2111.01370/) (2021)
- [Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversity](https://mlsanity.com/paper/2405.16585/) (2024)
- [Federated Graph Semantic and Structural Learning](https://mlsanity.com/paper/2406.18937/) (2024)
- [FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors](https://mlsanity.com/paper/2503.15842/) (2025)
- [OpenFGL: A Comprehensive Benchmark for Federated Graph Learning](https://mlsanity.com/paper/2408.16288/) (2024)
- [FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference](https://mlsanity.com/paper/2410.20105/) (2024)
- [Federated Graph Learning with Structure Proxy Alignment](https://mlsanity.com/paper/2408.09393/) (2024)
- [A Comprehensive Data-centric Overview of Federated Graph Learning](https://mlsanity.com/paper/2507.16541/) (2025)
- [GRAIN: Exact Graph Reconstruction from Gradients](https://mlsanity.com/paper/2503.01838/) (2025)

## Abstract (arXiv)

Federated graph learning (FGL) trains a shared graph model across clients whose local graphs differ in node features, labels, and connectivity while keeping raw graph data decentralized. Although graph-domain shifts across clients can severely degrade the global model, existing FGL approaches for graph-domain shift mainly adapt local representations, propagation, or graph-derived collaboration, while the server typically applies the same aggregation rule to every parameter coordinate. In this work, we analyze how graph-domain shifts affect server-side aggregation. We find that, as clients optimize under distinct graph-domain conditions, they gradually concentrate their strongest updates on different parameter coordinates, making important update coordinates less shared across clients. Consequently, standard averaging can weaken these domain-specific signals even when client updates are not directly opposed. These findings reveal an aggregationinduced signal dilution effect: parameter coordinates strongly expressed by only a subset of domains are attenuated by nearzero contributions from the remaining domains. Motivated by these findings, we propose FedIA, a lightweight serverside aggregation method that calibrates parameter selection and client weighting. FedIA identifies important coordinates =within each layer and adjusts client aggregation weights according to their contributions on the selected subspace, without modifying local graph training or the standard clientupdate payload. Experiments on Twitch Gamers and WikiNet using two graph-learning backbones and nine FL/FGL baselines show improvements of up to 11.58 percentage points, with particularly strong gains under domain skew.