Federated Learning with Cross-Device Transfer Learning in IoT
Bibliographic record
Abstract
With more smart devices connecting to our daily lives, it's becoming increasingly important to use machine learning that not only keeps our personal data safe but also works smoothly across all kinds of different devices. Federated Learning (FL) offers a decentralized alternative, enabling devices to jointly train models without requiring local data sharing. FL, nevertheless, suffers from the problem of knowledge transfer across heterogeneous IoT devices, which are likely to possess different data distributions. This work proposes Cross-Device Transfer Learning (CDTL), a novel combination of FL and Transfer Learning (TL), to enhance model generalization across heterogeneous devices. The CDTL framework proposed here enables the effective transfer of knowledge learned by one device, such as a smart thermostat, to another, like a security camera, without the need for data collection in the cloud. This accelerates learning, improves model performance, and preserves data privacy. This theoretical analysis shows that CDTL can enhance accuracy by$10-15 {\%}$, reduce training time by 28%, and improve improving convergence rate by up to 40%. These findings show the promise of CDTL in creating more intelligent and cooperative IoT 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 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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".