FedCIM: Handling Data Heterogeneity in Federated Learning to Improve Fairness and Robustness
Bibliographic record
Abstract
Federated learning has emerged as a framework for collaborative learning among decentralized clients, allowing the generation of a shared model while maintaining data privacy and control. Data heterogeneity across clients is considered a key factor that degrades the performance of collaborative learning and can lead to biased global models. The existence of non-identically and independently distributed (non-IID) data across clients presents substantial challenges to fairness and robustness in federated learning. To mitigate data heterogeneity challenges, we present an efficient approach named clustered FL with an iterative mechanism (FedCIM) that interprets the diverse data distribution of clients as separate tasks and applies multitask learning to provide personalized models. Our methodology iteratively groups clients according to similarities in their data distributions and develops personalized models for each realized distribution cluster. We alleviate the need for the participation of all clients in each training round. This adaptive clustering approach iteratively refines client groupings during the federation process, ensuring suitable task partitioning. We illustrate the effectiveness of our approach through empirical evaluation, achieving better accuracy (95.33%), fairness, and robustness relative to conventional federated learning methods, especially under conditions of extreme data heterogeneity, thus enhancing its applicability for real-world federated learning implementations.
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 | 0.013 | 0.032 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.004 | 0.006 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".