Abstract
Federated learning is gaining attention for its ability to extract knowledge from distributed data streams without sharing client data. In this process, each client continuously collects samples from its local data stream for local training. The samples collected by clients at different points in time are only the tip of the iceberg of the overall dataset. The imbalance between these data chunks can be dynamically changing. At the same time, different imbalanced distributions may exist among clients, leading to spatial heterogeneity in data. To fill this research gap in federated learning, this paper presents the following innovation: 1) We identify nine characteristics of class imbalance in federated data streams and study their impact on global performance in a series of artificial scenarios; 2) We develop two new techniques, clustering-based incremental sampling and distance-based incremental sampling, to address the dynamic class imbalance in the federated data stream by retaining key samples locally at the client. Our incremental sampling method performs well and has set new records in real datasets regardless of the aggregation method.
| Original language | English |
|---|---|
| Title of host publication | 2024 20th International Conference on Mobility, Sensing and Networking (MSN) |
| Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| Number of pages | 6 |
| ISBN (Electronic) | 9798331516024 |
| ISBN (Print) | 9798331516031 (PoD) |
| DOIs | |
| Publication status | Published - 24 Jun 2025 |
| Event | 20th International Conference on Mobility, Sensing and Networking - Harbin, China Duration: 20 Dec 2024 → 22 Dec 2024 https://ieee-msn.org/2024 |
Publication series
| Name | International Conference on Mobile Ad-hoc and Sensor Networks |
|---|---|
| Publisher | IEEE |
| ISSN (Print) | 2994-3515 |
| ISSN (Electronic) | 2994-3523 |
Conference
| Conference | 20th International Conference on Mobility, Sensing and Networking |
|---|---|
| Abbreviated title | MSN 2024 |
| Country/Territory | China |
| City | Harbin |
| Period | 20/12/24 → 22/12/24 |
| Internet address |
Bibliographical note
Workshop on Network Meets Intelligent Computations (NMIC).Keywords
- Federated learning
- Data stream
- Class Imbalance
- Re-balance
Fingerprint
Dive into the research topics of 'Incremental Sampling for Class Imbalanced Data Streams in Federated Learning'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver