Federated Graph Out-of-Distribution Generalization via Representation Propagation and Scattering
Bibliographic record
Abstract
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.010 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.005 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".