Straggler-resilient Federated Learning: Tackling Computation Heterogeneity with Layer-wise Partial Model Training in Mobile Edge Network
Bibliographic record
Abstract
Federated Learning (FL) enables many resource-limited devices to train a model collaboratively without data sharing. However, many existing works focus on model-homogeneous FL, where the global and local models are the same size, ignoring the inherently heterogeneous computational capabilities of different devices and restricting resource-constrained devices from contributing to FL. In this paper, we consider model-heterogeneous FL and propose Federated Partial Model Training (<monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedPMT</monospace>), where devices with smaller computational capabilities work on partial models (subsets of the global model) and contribute to the global model. Different from Dropout-based partial model generations, which remove neurons in (hidden) model layers at random, model training in <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedPMT</monospace> is achieved from the back-propagation perspective. As such, all devices in <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedPMT</monospace> prioritize the most crucial parts of the global model. Theoretical analysis shows that the proposed partial model training design has a similar convergence rate to the widely adopted Federated Averaging (FedAvg) algorithm, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathcal {O}(1/T)$</tex-math></inline-formula>, with the sub-optimality gap enlarged by a constant factor related to the model splitting design in <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedPMT</monospace>. Empirical results show that <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedPMT</monospace> significantly outperforms the existing partial model training designs, FedDrop and HeteroFL, especially on complex tasks. Meanwhile, compared to the popular model-homogeneous benchmark, FedAvg, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedPMT</monospace> reaches the learning target in a shorter completion time, thus achieving a better trade-off between learning accuracy and completion time.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".