Advancing IIoT with Over-the-Air Federated Learning: The Role of Iterative Magnitude Pruning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The industrial Internet of Things (IIoT) leverages interconnected smart devices combined with machine learning (ML) to transform manufacturing. A key enhancement within IIoT is the adoption of federated learning (FL), which ensures data privacy and security by enabling edge sensors, or peripheral intelligence units (PIUs), to process data locally without sharing sensitive information over the network. Nonetheless, PIUs are constrained by limited memory, computational power, and challenges like bandwidth restrictions and environmental noise, necessitating the use of compact yet robust deep neural network (DNN) models. To address this, model compression techniques such as pruning are employed to streamline DNNs by removing superfluous connections, optimizing them for PIU resources. Specifically, we propose iterative magnitude pruning (IMP) within an over-the-air FL (OTA-FL) network to enhance DNN efficiency in IIoT. We provide a tutorial overview and also present a case study on the efficacy of IMP in managing the unique challenges of noise and bandwidth in IIoT. This work also provides future directions for enhancing and optimizing deep compression techniques to acquire compact, robust, and high-performing DNN models for IIoT in OTA-FL networks.
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.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.011 | 0.013 |
| 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 it