Dynamic Conjugate Gradient Unfolding for Symbol Detection in Time-Varying Massive MIMO
Bibliographic record
Abstract
This article addresses the problem of symbol detection in time-varying Massive Multiple-Input Multiple-Output (M-MIMO) systems. While conventional detection techniques either exhibit subpar performance or impose excessive computational burdens in such systems, learning-based methods which have shown great potential in stationary scenarios, struggle to adapt to non-stationary conditions. To address these challenges, we introduce innovative extensions to the Learned Conjugate Gradient Network (LcgNet) M-MIMO detector. Firstly, we expound Preconditioned LcgNet (PrLcgNet), which incorporates a preconditioner during training to enhance the uplink M-MIMO detector's filter matrix. This modification enables the detector to achieve faster convergence with fewer layers compared to the original approach. Secondly, we introduce an adaptation of PrLcgNet referred to as Dynamic Conjugate Gradient Network (DyCoGNet), specifically designed for time-varying environments. DyCoGNet leverages self-supervised learning with Forward Error Correction (FEC), enabling autonomous adaptation without the need for explicit labeled data. It also employs meta-learning, facilitating rapid adaptation to unforeseen channel conditions. Our simulation results demonstrate that in stationary scenarios, PrLcgNet achieves faster convergence than LCgNet, which can be leveraged to reduce system complexity or improve Symbol Error Rate (SER) performance. Furthermore, in non-stationary scenarios, DyCoGNet exhibits rapid and efficient adaptation, achieving significant SER performance gains compared to baseline cases without meta-learning and a recent benchmark using self-supervised learning.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| 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".