Semantic Feature Multiple Access Empowered Integrated Learning and Communication Networks

TL;DR

This paper introduces a novel semantic feature multiple access scheme with a Swin Transformer-based transceiver, optimizing resource allocation for integrated learning and communication networks, resulting in significant performance gains.

Contribution

It proposes similarity-conditioned SFMA with a new transceiver design and a comprehensive optimization framework for resource management in ILAC systems.

Findings

SC-SFMA outperforms deep JSCC and separation-based baselines in PSNR and MS-SSIM.

The optimization framework achieves higher sum rates than traditional multiple access methods.

The pair-dependent interference is effectively modeled and managed through the proposed approach.

Abstract

Integrated learning and communication (ILAC) unifies learned transceivers with radio resource management, where semantic feature multiple access (SFMA) enables paired users to superpose their learned representations over shared time-frequency resources. Unlike conventional multiple access schemes, SFMA interference arises in the learned feature space and depends jointly on the user pair, the transmit power, and the compression ratio. This coupling ties binary pairing decisions to continuous resource variables, yielding a mixed-integer non-convex optimization problem. To address this problem, we first propose similarity-conditioned SFMA (SC-SFMA), a Swin Transformer-based transceiver whose dual-conditioned similarity modulator (DC-SimM) gates cross-user feature fusion according to the inter-user semantic similarity. We then characterize the resulting pair-dependent interference by a bivariate logistic function parameterized by transmit power and compression ratio, thereby bridging the learned transceiver with network-level optimization. On this basis, we formulate a sum-rate maximization problem subject to per-user distortion, latency, energy, power, and bandwidth constraints. To solve this problem, we develop a three-block alternating optimization algorithm that integrates dual-decomposition-assisted compression ratio allocation, trust-region successive convex approximation (SCA) for joint power-bandwidth optimization, and dynamic feasible graph-based user pairing. Simulation results show that SC-SFMA achieves considerable peak signal-to-noise ratio (PSNR) and multi-scale structural similarity index measure (MS-SSIM) gains over deep joint source-channel coding (JSCC) and separation-based baselines. The proposed optimization framework attains significant sum rate improvements over conventional multiple access baselines.