# Forward-Forward Autoencoder Architectures for Energy-Efficient Wireless Communications

arXiv: https://arxiv.org/abs/2510.11418 · HTML: https://mlsanity.com/paper/2510.11418/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 19 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 12 of 12)

- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [The Forward-Forward Algorithm: Some Preliminary Investigations](https://mlsanity.com/paper/2212.13345/) (2022)
- [An Introduction to Deep Learning for the Physical Layer](https://mlsanity.com/paper/1702.00832/) (2017)
- [Decoupled Neural Interfaces using Synthetic Gradients](https://mlsanity.com/paper/1608.05343/) (2016)
- [Deep Learning-Based Communication Over the Air](https://mlsanity.com/paper/1707.03384/) (2017)
- [Hebbian Deep Learning Without Feedback](https://mlsanity.com/paper/2209.11883/) (2022)
- [Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channels](https://mlsanity.com/paper/1911.03038/) (2019)
- [Model-free Training of End-to-end Communication Systems](https://mlsanity.com/paper/1812.05929/) (2018)
- [Signal Propagation: A Framework for Learning and Inference In a Forward Pass](https://mlsanity.com/paper/2204.01723/) (2022)
- [WGAN-based Autoencoder Training Over-the-air](https://mlsanity.com/paper/2003.02744/) (2020)
- [Bit Error and Block Error Rate Training for ML-Assisted Communication](https://mlsanity.com/paper/2210.14103/) (2022)
- [Concatenated Classic and Neural (CCN) Codes: ConcatenatedAE](https://mlsanity.com/paper/2209.01701/) (2022)

## Abstract (arXiv)

The application of deep learning to the area of communications systems has been a growing field of interest in recent years. Forward-forward (FF) learning is an efficient alternative to the backpropagation (BP) algorithm, which is the typically used training procedure for neural networks. Among its several advantages, FF learning does not require the communication channel to be differentiable and does not rely on the global availability of partial derivatives, allowing for an energy-efficient implementation. In this work, we design end-to-end learned autoencoders using the FF algorithm and numerically evaluate their performance for the additive white Gaussian noise and Rayleigh block fading channels. We demonstrate their competitiveness with BP-trained systems in the case of joint coding and modulation, and in a scenario where a fixed, non-differentiable modulation stage is applied. Moreover, we provide further insights into the design principles of the FF network, its training convergence behavior, and significant memory and processing time savings compared to BP-based approaches.