Research map / Federated learning and privacy / Personalized and heterogeneous FL
Inter-Client Dependency Recovery with Hidden Global Components for Federated Traffic Prediction
Hang Zhou, Wentao Yu, Yang Wei, Guangyu Li, Sha Xu, Chen Gong
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 |
|---|---|---|---|
| add generated proxy nodes from hidden global components (ablation) | FedHINT · PEMS03 | MAE: 12.70 -> 11.95 | Improved |
| add generated proxy nodes (ablation) | FedHINT · PEMS07 | MAE: 18.13 -> 17.19 | Improved |
| add time-shifted filters (ablation) | FedHINT · PEMS08 | MAE: 12.49 -> 12.38 | Improved |
| add separate global encoder alongside local encoder (ablation) | FedHINT · PEMS08 | MAE: 13.15 -> 12.38 | Improved |
| add personalized aggregation (share only global params) (ablation) | FedHINT · PEMS04 | MAE: 16.84 -> 16.11 | Improved |
| FedHINT vs second-best federated method | FedHINT · PEMS03 | MAE: 15.48 -> 11.95 | Improved |
| recover inter-client dependency without uploading features | FedHINT vs CNFGNN/FedGTP · PEMS03 overhead | communication overhead | Improved |
| add hidden-component extractor and proxy nodes vs methods ignoring inter-client dependency | FedHINT vs FedGRU/CTFL/FedTPS · PEMS03 overhead | communication overhead and training time | Hurt |
| vary lambda of diversity loss 1e-3 to 10 (ablation) | FedHINT · PEMS03 | MAE | No clear effect |
Closest papers by meaning
- MIETT: Multi-Instance Encrypted Traffic Transformer for Encrypted Traffic Classification (AAAI 2025 · similarity 0.84)
- OmniFC: Rethinking Federated Clustering via Lossless and Secure Distance Reconstruction (NeurIPS 2025 · similarity 0.83)
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts (NeurIPS 2025 · similarity 0.83)
- Data Disparity and Temporal Unavailability Aware Asynchronous Federated Learning for Predictive Maintenance on Transportation Fleets (AAAI 2024 · similarity 0.83)
- Why Go Full? Elevating Federated Learning Through Partial Network Updates (NeurIPS 2024 · similarity 0.83)
- FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity (ICLR 2024 · similarity 0.82)
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.
