Supervised Contrastive CSI Representation Learning for Massive MIMO Positioning
This work addresses positioning accuracy in massive MIMO systems, which is incremental as it builds on existing contrastive learning and CSI methods.
The paper tackles the problem of similarity metric learning for massive MIMO positioning using channel state information (CSI), proposing a method based on deep convolutional neural networks and contrastive learning that significantly improves positioning accuracy on a real-world dataset compared to state-of-the-art methods.
Similarity metric is crucial for massive MIMO positioning utilizing channel state information~(CSI). In this letter, we propose a novel massive MIMO CSI similarity learning method via deep convolutional neural network~(DCNN) and contrastive learning. A contrastive loss function is designed considering multiple positive and negative CSI samples drawn from a training dataset. The DCNN encoder is trained using the loss so that positive samples are mapped to points close to the anchor's encoding, while encodings of negative samples are kept away from the anchor's in the representation space. Evaluation results of fingerprint-based positioning on a real-world CSI dataset show that the learned similarity metric improves positioning accuracy significantly compared with other known state-of-the-art methods.