# Neural Joint Source-Channel Coding

arXiv: https://arxiv.org/abs/1811.07557 · HTML: https://mlsanity.com/paper/1811.07557/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2018.

## Built on by (most cited first, 6 of 6)

- [DeepJSCC-Q: Constellation Constrained Deep Joint Source-Channel Coding](https://mlsanity.com/paper/2206.08100/) (2022)
- [DeepJSCC-Q: Channel Input Constrained Deep Joint Source-Channel Coding](https://mlsanity.com/paper/2111.13042/) (2021)
- [Learning Based Joint Coding-Modulation for Digital Semantic Communication Systems](https://mlsanity.com/paper/2208.05704/) (2022)
- [Goal-Oriented Quantization: Analysis, Design, and Application to Resource Allocation](https://mlsanity.com/paper/2209.15347/) (2022)
- [Multi-Sample Training for Neural Image Compression](https://mlsanity.com/paper/2209.13834/) (2022)
- [Learned Image Transmission with Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2408.16340/) (2024)

## Abstract (arXiv)

For reliable transmission across a noisy communication channel, classical results from information theory show that it is asymptotically optimal to separate out the source and channel coding processes. However, this decomposition can fall short in the finite bit-length regime, as it requires non-trivial tuning of hand-crafted codes and assumes infinite computational power for decoding. In this work, we propose to jointly learn the encoding and decoding processes using a new discrete variational autoencoder model. By adding noise into the latent codes to simulate the channel during training, we learn to both compress and error-correct given a fixed bit-length and computational budget. We obtain codes that are not only competitive against several separation schemes, but also learn useful robust representations of the data for downstream tasks such as classification. Finally, inference amortization yields an extremely fast neural decoder, almost an order of magnitude faster compared to standard decoding methods based on iterative belief propagation.