Multi-Criteria Clustering and Client Selection for Heterogeneous Federated Learning
Bibliographic record
Abstract
Federated learning (FL) faces significant challenges due to the non-independent and identically distributed (non-IID) data and the heterogeneous nature of clients’ characteristics. Clustered federated learning (CFL) addresses these issues by grouping similar clients and creating cluster-specific models. However, CFL introduces additional challenges, such as determining the optimal clustering criteria and managing the dynamic nature of client availability and data distribution. This paper proposes a novel CFL approach that integrates a full spectrum of relevant factors where clients are clustered based on data distribution, device type, and geographical location. Each group selects a subset of clients based on the information’s age, the client’s motivation, and the availability of resources to participate in the learning process. Unlike previous approaches that focus on a limited set of criteria, our method considers a holistic view of client attributes to improve clustering performance. The experimental results demonstrate the efficiency and effectiveness of the proposed method, highlighting significant improvements in communication efficiency and model quality. Furthermore, our approach adapts dynamically to changes in client availability, ensuring robust learning over time. By optimizing client selection and leveraging cluster-specific characteristics, the proposed approach enhances the scalability, robustness, and overall performance of FL systems.
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 | 0.005 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.001 |
| 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".