CSI2Vec: Towards a Universal CSI Feature Representation for Positioning and Channel Charting

2025-06-05

AI Summary

Existing CSI-based positioning (POS) and channel charting (CC) methods suffer from poor generalizability of feature representations, reliance on CSI reconstruction or ground-truth location labels, weak cross-scenario/hardware adaptability, and high computational and storage overhead. To address these challenges, this paper proposes CSI2Vec—the first self-supervised CSI vector representation framework jointly designed for POS and CC. Inspired by Word2Vec, CSI2Vec employs neural networks to learn compact, environment- and hardware-agnostic spatial embeddings directly from raw CSI, eliminating the need for CSI reconstruction, ground-truth position supervision, or full CSI transmission. It leverages ray-tracing simulations and joint training across diverse deployments and hardware platforms to enhance spatial relationship modeling. Evaluated on both synthetic and real-world datasets, CSI2Vec significantly reduces computational and memory costs while maintaining state-of-the-art accuracy in positioning and channel charting.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Representation Learning for Vision
• Intelligent Robots: State Estimation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Natural language processing techniques, such as Word2Vec, have demonstrated exceptional capabilities in capturing semantic and syntactic relationships of text through vector embeddings. Inspired by this technique, we propose CSI2Vec, a self-supervised framework for generating universal and robust channel state information (CSI) representations tailored to CSI-based positioning (POS) and channel charting (CC). CSI2Vec learns compact vector embeddings across various wireless scenarios, capturing spatial relationships between user equipment positions without relying on CSI reconstruction or ground-truth position information. We implement CSI2Vec as a neural network that is trained across various deployment setups (i.e., the spatial arrangement of radio equipment and scatterers) and radio setups (RSs) (i.e., the specific hardware used), ensuring robustness to aspects such as differences in the environment, the number of used antennas, or allocated set of subcarriers. CSI2Vec abstracts the RS by generating compact vector embeddings that capture essential spatial information, avoiding the need for full CSI transmission or reconstruction while also reducing complexity and improving processing efficiency of downstream tasks. Simulations with ray-tracing and real-world CSI datasets demonstrate CSI2Vec's effectiveness in maintaining excellent POS and CC performance while reducing computational demands and storage.

Problem

• Develop universal CSI representations for positioning and charting
• Learn spatial relationships without CSI reconstruction or position data
• Ensure robustness across diverse wireless setups and environments

Innovation

• Self-supervised CSI2Vec for universal CSI representation
• Neural network trained across diverse deployment setups
• Compact embeddings reduce complexity and improve efficiency