Deep-OFDM: Neural Modulation for High Mobility

Orthogonal Frequency Division Multiplexing (OFDM) is the foundational waveform in current 5G deployments due to its robustness in quasi-static channels and efficient spectrum use. However, in high-mobility scenarios, OFDM suffers from inter-carrier interference (ICI), and its reliance on dense pilot patterns and cyclic prefixes significantly reduces spectral efficiency. In this work, we propose Deep-OFDM: a learnable modulation framework that augments traditional OFDM by incorporating neural parameterization. Instead of mapping each symbol to a fixed resource element, Deep-OFDM spreads information across the OFDM grid using a convolutional neural network modulator. This modulator is jointly optimized with a neural receiver through end-to-end training, enabling the system to adapt to time-varying channels without relying on explicit channel estimation. Deep-OFDM outperforms conventional OFDM when paired with neural receiver baselines, particularly in pilot-sparse and pilotless regimes, achieving substantial gains in BLER and goodput, especially at high Doppler frequencies. In the pilotless setting, the neural modulator learns a low-rank structure that resembles a superimposed pilot, effectively enabling reliable communication without explicit overhead. Deep-OFDM demonstrates significant improvements in BLER and goodput at high Doppler frequencies across various scenarios, including MIMO systems. Comprehensive ablation studies quantify the role of nonlinear activations and characterize performance-complexity trade-offs. These results highlight the potential of transmitter-receiver co-design for robust, resource-efficient communication, paving the way for AI-native physical layer designs in next-generation wireless systems.