{"ID":5937203,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T08:25:06.104751926Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04795","arxiv_id":"2607.04795","title":"Shift-MoE-Based DJSCC for CSI Feedback in Multi-User Pinching-Antenna Systems","abstract":"In frequency-division duplexing systems, the performance gains of pinching-antenna systems (PASS) critically depend on accurate channel state information (CSI) at the base station. However, PASS CSI exhibits structured correlations over the waveguide-antenna grid and pronounced heterogeneity across users, making conventional fixed feedback mappings difficult to generalize. To address this challenge, this letter proposes an end-to-end CSI feedback scheme over a noisy uplink feedback link based on deep joint source-channel coding, termed Shift-based Mixture-of-Experts (Shift-MoE). Specifically, Shift-MoE leverages channel-grouped one-step shift operations to capture grid dependencies without global attention, and employs a gated multilayer perceptron mixture-of-experts module to adapt to heterogeneous CSI statistics across users. Numerical results demonstrate that the proposed Shift-MoE consistently outperforms representative learning-based CSI feedback baselines in normalized mean squared error and remains effective under different system parameter settings.","short_abstract":"In frequency-division duplexing systems, the performance gains of pinching-antenna systems (PASS) critically depend on accurate channel state information (CSI) at the base station. However, PASS CSI exhibits structured correlations over the waveguide-antenna grid and pronounced heterogeneity across users, making conven...","url_abs":"https://arxiv.org/abs/2607.04795","url_pdf":"https://arxiv.org/pdf/2607.04795v1","authors":"[\"Jian Zou\",\"Yifan Lian\",\"Yongsheng Liang\",\"Fanyang Meng\",\"Wenwu Xie\",\"Liang Yang\",\"Jian Xiao\"]","published":"2026-07-06T08:30:16Z","proceeding":"eess.SP","tasks":"[\"eess.SP\"]","methods":"[]","has_code":false}