MétaCan
Menu
Back to cohort
Record W7131417874 · doi:10.1109/icdm65498.2025.00107

Federated Graph Out-of-Distribution Generalization via Representation Propagation and Scattering

2025· article· W7131417874 on OpenAlexaff
Yukai Zhu, He Sun, Mingjun Xiao

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicAdvanced Graph Neural Networks
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsGeneralizationRobustness (evolution)GraphRepresentation (politics)Feature learningUpper and lower boundsFeature (linguistics)Topology (electrical circuits)Generalization error

Abstract

fetched live from OpenAlex

Federated Graph Learning (FGL) enables collab-orative model training across decentralized graph data while preserving privacy. However, FGL faces severe performance degradation under out-of-distribution (OOD) shifts due to both feature distribution divergence and structural heterogeneity among clients. To address this, we propose FGOOD, a lightweight and effective framework that improves OOD generalization in FGL. FGOOD integrates two key components: (1) representation propagation, which enhances structural robustness by aggregating multi-hop topology while preserving local features, and (2) representation scattering, which regularizes node embeddings toward a uniformly dispersed distribution on the hypersphere, improving inter-class separation without requiring contrastive pairs. The theoretical analysis provides an upper bound on the generalization error under distribution shifts. Extensive experiments on three real-world datasets demonstrate that FGOOD outperforms existing state-of-the-art baselines, improving OOD accuracy by up to 5% while remaining lightweight and scalable.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.010
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.005
Threshold uncertainty score0.014

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.010
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0010.002
Science and technology studies0.0010.002
Scholarly communication0.0020.005
Open science0.0040.005
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.019
GPT teacher head0.284
Teacher spread0.265 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicAdvanced Graph Neural NetworksFrench-language works237,207