Research map / Time series / Long-term forecasting
FedSkeleton: Secure Multi-Party Graph Skeleton Construction for Privacy-Preserving Federated Time-Series Forecasting
Henggang Deng, Yuchao Tang, Wenjie Fu, Huandong Wang, Kun Chen, Tao Jiang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| raise compression ratio gamma from below 0.1 to 0.2 or above (ablation) | FedSkeleton · Solar | MAE/MSE | Improved |
| raise gamma beyond 0.2 (ablation) | FedSkeleton · Solar | MAE/MSE | No clear effect |
| add global fusion (alpha from 0 to moderate 0.3-0.6) (ablation) | FedSkeleton · Solar and ChileNet | MAE/MSE | Improved |
| push fusion rate alpha toward 1 (ablation) | FedSkeleton · Solar | MAE/MSE | Hurt |
| increase federation size from 5 to 50 parties | FedSkeleton · Syn | MAE: 0.0348 -> 0.0572 | Hurt |
| increase federation size from 5 to 50 parties | FedSkeleton · Syn | MSE: 0.0030 -> 0.0090 | Hurt |
| increase federation size from 5 to 50 parties | CNFGNN · Syn | MAE: 0.0911 -> 0.0811 | Improved |
| increase gamma (less compression) on attack privacy (ablation) | FedSkeleton · Solar attack | attacker MAE: errors drop for gamma >= 0.2 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FourierGNN — FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective (NeurIPS 2023) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Subgraph Federated Learning via Spectral Methods (NeurIPS 2025 · similarity 0.89)
- Federated Graph Condensation with Information Bottleneck Principles (AAAI 2025 · similarity 0.88)
- Less is More: Federated Graph Learning with Alleviating Topology Heterogeneity from A Causal Perspective (ICML 2025 · similarity 0.86)
- Federated Graph Learning under Domain Shift with Generalizable Prototypes (AAAI 2024 · similarity 0.86)
- Differentially Private Decentralized Learning with Random Walks (ICML 2024 · similarity 0.86)
- Privacy Amplification by Structured Subsampling for Deep Differentially Private Time Series Forecasting (ICML 2025 · similarity 0.85)
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.
