LoRa Modulation for Split Learning

We design a task-oriented communication design for Split learning (SL). Specifically, we propose to use a variant of the Long Range (LoRa) modulation and an orthogonal chirp division multiplexing (OCDM) access scheme. As we implement an Expressive Neural Network (ENN), this is, an architecture with adaptive activation functions (AAF), the modulation is also suited for the computing side of the problem. The cosine nature of the modulation matches the Discrete Cosine Transform (DCT) model used to implement the AAFs. We also propose a variant of the waveform to control the transmission bandwidth. Our results show that scheme achieves high accuracy up to -15 dB in the presence of additive white Gaussian noise (AWGN), and up to -12.5 dB in the case of Rayleigh fading.