Research map / Federated learning and privacy / Personalized and heterogeneous FL
FeDaL: Federated Dataset Learning for General Time Series Foundation Models
Shengchao Chen, Guodong Long, Michael Blumenstein, Jing 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 |
|---|---|---|---|
| add Domain Bias Elimination (DBE) block (ablation) | FeDaL · UTSD+CTSD representation learning | reconstruction MSE (avg): 0.545 -> 0.489 | Improved |
| add Global Bias Elimination (GBE) (ablation) | FeDaL · UTSD+CTSD representation learning | reconstruction MSE (avg): 0.527 -> 0.489 | Improved |
| add bias alignment penalty in DBE (ablation) | FeDaL · UTSD+CTSD representation learning | reconstruction MSE (avg): 0.518 -> 0.489 | Improved |
| add core-set tuning on server (ablation) | FeDaL · UTSD+CTSD representation learning | reconstruction MSE (avg): 0.510 -> 0.489 | Improved |
| add gradient-level dynamic correction (ablation) | FeDaL · UTSD+CTSD representation learning | reconstruction MSE (avg): 0.516 -> 0.489 | Improved |
| overly large alignment weight lambda (ablation) | FeDaL · UTSD | reconstruction MSE | Hurt |
| larger core-set size (ablation) | FeDaL · UTSD | reconstruction MSE | No clear effect |
| extreme fusion weight alpha (ablation) | FeDaL · UTSD | reconstruction MSE | Hurt |
| FeDaL vs FFTS federated pretraining | federated TSFM pretraining · UTSD and CTSD | reconstruction MSE: 4.16% on USTD and 8.86% on CTSD | Improved |
| transmit core-sets to server | FeDaL · communication per round | communication parameters: 108.41 MB (FedAvg) -> 110.41 MB | Mixed |
| increase pretraining data size from 40B to 231B points (ablation) | FeDaL · federated scaling (174 clients) | downstream performance | Improved |
| increase client count from 30 to 174 at fixed total data (ablation) | FeDaL · federated scaling | downstream performance | Improved |
Closest papers by meaning
- Federated Foundation Models on Heterogeneous Time Series (AAAI 2025 · similarity 0.92)
- Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting (NeurIPS 2024 · similarity 0.88)
- An Aggregation-Free Federated Learning for Tackling Data Heterogeneity (CVPR 2024 · similarity 0.87)
- FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning (NeurIPS 2025 · similarity 0.87)
- Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach (NeurIPS 2024 · similarity 0.86)
- FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data (ICLR 2024 · similarity 0.86)
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.
