Pith. sign in

REVIEW 4 cited by

GPASS: Deep Learning for Beamforming in Pinching-Antenna Systems (PASS)

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.01438 v1 pith:5LNLI5QI submitted 2025-02-03 eess.SP

classification eess.SP
keywords beamformingarchitecturegpasslearnedlearningpinchingtransmitantenna
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A novel GPASS architecture is proposed for jointly learning pinching beamforming and transmit beamforming in pinching antenna systems (PASS). The GPASS is with a staged architecture, where the positions of pinching antennas are first learned by a sub-GNN. Then, the transmit beamforming is learned by another sub-GNN based on the antenna positions. The sub-GNNs are incorporated with the permutation property of the beamforming policy, which helps improve the learning performance. The optimal solution structure of transmit beamforming is also leveraged to simplify the mappings to be learned. Numerical results demonstrate that the proposed architecture can achieve a higher SE than a heuristic baseline method with low inference complexity.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Multigroup Multicast Design for Pinching-Antenna Systems: Waveguide-Division or Waveguide-Multiplexing?

    eess.SP 2025-06 conditional novelty 6.0 of 10

    Pinching-antenna systems can beat conventional and massive MIMO for multigroup multicast by repositioning antennas along waveguides, with waveguide-multiplexing best for dense users and waveguide-division best for sep...

  2. Deep Learning Optimization of Two-State Pinching Antennas Systems

    cs.LG 2025-07 conditional novelty 5.0 of 10

    A graph neural network with distributed attention selects near-optimal subsets of active pinching antennas, matching a Gurobi solver's rates within a few percent and generalizing from 50 to 1000 antennas.

  3. Exploiting Pinching-Antenna Systems in Multicast Communications

    eess.SP 2025-05 conditional novelty 5.0 of 10

    Optimizing pinching-antenna positions along dielectric waveguides improves multicast rates, with closed-form results for a single antenna and iterative algorithms for multiple antennas or waveguides.

  4. A Gradient Meta-Learning Joint Optimization for Beamforming and Antenna Position in Pinching-Antenna Systems

    cs.IR 2025-06 conditional novelty 4.0 of 10

    A gradient meta-learning algorithm with two unrolled neural networks jointly optimizes beamforming and pinching-antenna positions, reporting 5.6 bits/s/Hz weighted sum rate and a 32.7% gain over alternating optimizati...

Pith tools