Over-the-Air Inference over Multi-hop MIMO Networks
This work addresses efficient distributed AI inference in wireless networks, but it is incremental as it builds on existing over-the-air computing and MIMO techniques.
The paper tackled the problem of implementing machine learning inference over multi-hop MIMO networks by designing a framework that uses precoding matrices to mimic neural network layers, achieving satisfactory classification accuracy under power constraints with improvements as hop count increases at modest SNR.
A novel over-the-air machine learning framework over multi-hop multiple-input and multiple-output (MIMO) networks is proposed. The core idea is to imitate fully connected (FC) neural network layers using multiple MIMO channels by carefully designing the precoding matrices at the transmitting nodes. A neural network dubbed PrototypeNet is employed consisting of multiple FC layers, with the number of neurons of each layer equal to the number of antennas of the corresponding terminal. To achieve satisfactory performance, we train PrototypeNet based on a customized loss function consisting of classification error and the power of latent vectors to satisfy transmit power constraints, with noise injection during training. Precoding matrices for each hop are then obtained by solving an optimization problem. We also propose a multiple-block extension when the number of antennas is limited. Numerical results verify that the proposed over-the-air transmission scheme can achieve satisfactory classification accuracy under a power constraint. The results also show that higher classification accuracy can be achieved with an increasing number of hops at a modest signal-to-noise ratio (SNR).