Deep Unfolding Learning Aided ISAC Transceiver Design
Bibliographic record
Abstract
Integrated sensing and communication (ISAC) can enhance spectral efficiency and facilitate the diverse emerging applications via sharing the same spectrum and hardware between communication and sensing. However, effective operation of ISAC may suffer from high complexity. In this paper, we develop a low-complexity deep unfolding learning-aided transceiver design scheme for ISAC in a cluttered environment. In particular, we optimize the transmit waveform and receive filtering to minimize the weighted sum of multi-user interference power and the reciprocal of sensing signal-to-interference-plus-noise ratio (SINR), while adhering to the constraints of a constant modulus signal and waveform similarity. An alternating direction method of multipliers (ADMM)-based iterative algorithm is first developed to address this non-convex optimization problem with both equality and inequality constraints. To further reduce the computational complexity, we develop two deep unfolding neural networks (NNs), termed ADMM-DL-NET and ADMM-PGD-NET, to handle this problem, which can unfold the underlying ADMM-based iterative algorithm to a lightweight neural network with learnable parameters and eliminate the need for the bisection method by adopting the Uzawa’s method and projected gradient descent, respectively. Simulation results demonstrate that our proposed deep unfolding NNs can achieve comparable performance to the ADMM-based iterative algorithm with significantly reduced complexity, and outperform the unsupervised learning benchmarks in performance and number of learnable parameters.
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 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".