CIG-MAE is a self‑supervised framework for WiFi‑based human action recognition that uses a cross‑modal masked autoencoder to reconstruct both amplitude and phase of Channel State Information. It introduces an adaptive, information‑guided masking strategy that focuses on high‑density time‑frequency regions and employs a Barlow Twins regularizer to align cross‑modal representations without negative samples. Experiments on three public datasets show that CIG‑MAE outperforms state‑of‑the‑art SSL methods and even surpasses a fully supervised baseline, highlighting its data efficiency, robustness, and generalization.
By Gang Liu, Yanling Hao, Yixuan Zou
arXiv:2609.22139v1 Announce Type: cross
Abstract: Automatic modulation classification (AMC) of received radio signals is prudent for further signal processing tasks such as communication monitoring,...
By Qamar Ijaz, Nayyer Aafaq
arXiv:2607. 08031v1 Announce Type: cross Abstract: The dynamics of communication environments induce significant distribution shifts across domains, challenging the generalization of deep learning-based automatic modulation classification (AMC) models.
By Shuang Wang, Chenxu Wang, Hantong Xing, Hanlin Mo, Lirong Han, Licheng Jiao
arXiv:2607. 16877v1 Announce Type: cross Abstract: The increasing complexity of next-generation wireless networks has driven the integration of artificial intelligence (AI) into wireless communications.
By Yangjing Wang, Ouya Wang, Shenglong Zhou, Geoffrey Ye Li
The paper introduces a theoretically grounded multi‑task learning framework, AMTIDIN, for joint interference detection, modulation identification, and interference identification. It derives an upper bound linking MTL performance to task similarity measured by Wasserstein distance and adaptive coefficients, and employs adversarial training to reduce distributional gaps across tasks. Experiments show AMTIDIN outperforms single‑task models and other MTL baselines, especially when training data is limited, signals are short, and SNRs are low.
By H. Xu, L. Hu, B. He, S. Wang
arXiv:2609.39489v1 Announce Type: new
Abstract: Sample-level reliability heterogeneity is common in deep time series learning. Standard training pipelines apply a uniform regularization setting to al...
By Siru Zhong, Senzhang Wang, James T. Kwok, Yuxuan Liang