Wavelet Convolution Enabled Distributed Machine Learning for Downlink Channel Estimation in RIS Assisted Communications
Bibliographic record
Abstract
In reconfigurable intelligent surface (RIS) assisted communication systems, downlink cascaded channel estimation faces not only high pilot overhead but also challenges arising from uneven user distribution and inter-scenario channel variations. A single neural network often struggles to generalize well across multiple channel scenarios, while conventional convolutional structures are constrained by limited receptive fields, making it difficult to jointly capture long-range dependencies and multi-scale features of the cascaded channel. To address these issues, we propose Wavelet-CE, which embeds wavelet convolution into a distributed training framework as the feature modeling unit, thereby enhancing the model's feature representation capability and significantly improving estimation accuracy during user mobility across scenarios. Building on this, we further design Wavelet-HCE, a hierarchical structure with a fusion decision mechanism, to effectively handle the ambiguous transition characteristics of channel samples at scenario boundaries, thereby further improving generalization performance. Simulation results demonstrate that the proposed methods achieve superior performance under low pilot overhead, significantly outperforming baseline approaches such as OMP, LPAN, HDCE, and HNet/HReNet.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".