CSI-BERT2: A BERT-inspired Framework for Efficient CSI Prediction and Classification in Wireless Communication and Sensing
Zijian Zhao, Fanyi Meng, Zhonghao Lyu, Hang Li, Xiaoyang Li, Guangxu Zhu

TL;DR
CSI-BERT2 introduces a novel BERT-inspired framework with a two-stage training process, including mask prediction, to improve CSI prediction and classification in wireless systems, effectively handling data scarcity, high mobility, and packet loss.
Contribution
The paper presents CSI-BERT2, a unified, efficient model that extends BERT with modifications and a new training strategy for superior CSI analysis in wireless communication and sensing.
Findings
Achieves state-of-the-art performance on real-world and simulated datasets.
Effectively handles packet loss and varying sampling rates.
Generalizes well across different wireless scenarios.
Abstract
Channel state information (CSI) is a fundamental component in both wireless communication and sensing systems, enabling critical functions such as radio resource optimization and environmental perception. In wireless sensing, data scarcity and packet loss hinder efficient model training, while in wireless communication, high-dimensional CSI matrices and short coherent times caused by high mobility present challenges in CSI estimation. To address these issues, we propose a unified framework named CSI-BERT2 for CSI prediction and classification tasks, built on CSI-BERT, which adapts BERT to capture the complex relationships among CSI sequences through a bidirectional self-attention mechanism. We introduce a two-stage training method that first uses a mask language model (MLM) to enable the model to learn general feature extraction from scarce datasets in an unsupervised manner, followed…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTime Series Analysis and Forecasting
