AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

One-Shot Federated Graph Learning via High-Fidelity Proxies and Transferability-Guided Collaboration

Jia Jiang, Zihan Tan, Wenke Huang, Bin Yang, Mang Ye

NeurIPS 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated semi-supervised and graph learning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a one-shot federated graph learning method that builds high-fidelity proxies and uses transferability-guided collaboration to overcome the single-transmission bottleneck.

Problem

One-shot federated graph learning (OFGL) compresses collaboration into a single transmission round under strict bandwidth limits, which restricts the quality and utility of the exchanged knowledge (a "single-transmission bottleneck").

Approach

Generates high-fidelity proxies for the single transmitted knowledge and uses transferability estimates to guide how clients collaborate; the abstract only partially describes this, so specifics are not stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use FedHFT instead of strongest one-shot baseline OASISone-shot federated graph learning · Cora, CiteSeer, Actor, Amazon-Photo, Roman-Empire, Ogbn-Arxivnode accuracy (%): Cora 40.05 -> 52.24; Actor 25.51 -> 41.51; Ogbn-Arxiv 28.87 -> 44.50Improved
use FedHFT instead of OASISone-shot federated graph learning · PubMednode accuracy (%): 65.96 -> 56.98Hurt
add Fidelity-Driven Proxy Refinement (FPR) (ablation)FedHFT · Cora, CiteSeer, Actor, Roman-Empirenode accuracy (%): Cora 29.01 -> 41.35Improved
add Transferability-Steered Personalized Collaboration (TPC) (ablation)FedHFT · Cora, CiteSeer, Actor, Roman-Empirenode accuracy (%): Cora 29.01 -> 45.25; CiteSeer 27.26 -> 54.19Improved
combine FPR and TPC (ablation)FedHFT · Coranode accuracy (%): 45.25 -> 52.24Improved
add Fisher gradient matching to FPR (ablation)FPR · Coranode accuracy (%): 29.01 -> 37.01Improved
add class-semantic alignment to FPR (ablation)FPR · Coranode accuracy (%): 29.01 -> 39.95Improved
add class-semantic alignment on top of Fisher matching (ablation)FPR · Roman-Empirenode accuracy (%): 29.27 -> 30.11Improved
select top-M channels with M at extremes (0 or 1) rather than 0.5-0.75 (ablation)FedHFT · Top-M ratio sensitivityaverage accuracyHurt
increase number of clients from 5 to 20FedHFT · Coranode accuracy (%): 62.17 -> 39.81Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy