A Survey on Federated Learning for Reconfigurable Intelligent Metasurfaces-Aided Wireless Networks
Bibliographic record
Abstract
Wireless networks are increasingly relying on machine learning (ML) paradigms to provide various services at the user level. Yet, it remains impractical for users to offload their collected data set to a cloud server for centrally training their local ML model. Federated learning (FL), which aims to collaboratively train a global ML model by leveraging the distributed wireless computation resources across users without exchanging their local information, is therefore deemed as a promising solution for enabling intelligent wireless networks in the data-driven society of the future. Recently, reconfigurable intelligent metasurfaces (RIMs) have emerged as a revolutionary technology, offering a controllable means for increasing signal diversity and reshaping transmission channels, without implementation constraints traditionally associated with multi-antenna systems. In this paper, we present a comprehensive survey of recent works on the applications of FL to RIM-aided communications. We first review the fundamental basis of FL with an emphasis on distributed learning mechanisms, as well as the operating principles of RIMs, including tuning mechanisms, operation modes, and deployment options. We then proceed with an in-depth survey of literature on FL-based approaches recently proposed for the solution of three key interrelated problems in RIM-aided wireless networks, namely: channel estimation (CE), passive beamforming (PBF) and resource allocation (RA). In each case, we illustrate the discussion by introducing an expanded FL (EFL) framework in which only a subset of active users partake in the distributed training process, thereby allowing to reduce transmission overhead. Lastly, we discuss some current challenges and promising research avenues for leveraging the full potential of FL in future RIM-aided extremely large-scale multiple-input-multiple-output (XL-MIMO) 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.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".