# Infomax Neural Joint Source-Channel Coding via Adversarial Bit Flip

arXiv: https://arxiv.org/abs/2004.01454 · HTML: https://mlsanity.com/paper/2004.01454/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2020.

## Built on by (most cited first, 7 of 7)

- [DeepJSCC-Q: Constellation Constrained Deep Joint Source-Channel Coding](https://mlsanity.com/paper/2206.08100/) (2022)
- [Deep Joint Source Channel Coding for WirelessImage Transmission with OFDM](https://mlsanity.com/paper/2101.03909/) (2021)
- [Adaptive Information Bottleneck Guided Joint Source and Channel Coding for Image Transmission](https://mlsanity.com/paper/2203.06492/) (2022)
- [Multi-Sample Training for Neural Image Compression](https://mlsanity.com/paper/2209.13834/) (2022)
- [Neuromorphic Wireless Device-Edge Co-Inference via the Directed Information Bottleneck](https://mlsanity.com/paper/2404.01804/) (2024)
- [Aligning Task- and Reconstruction-Oriented Communications for Edge Intelligence](https://mlsanity.com/paper/2502.15472/) (2025)
- [TOAST: Task-Oriented Adaptive Semantic Transmission over Dynamic Wireless Environments](https://mlsanity.com/paper/2506.21900/) (2025)

## Abstract (arXiv)

Although Shannon theory states that it is asymptotically optimal to separate the source and channel coding as two independent processes, in many practical communication scenarios this decomposition is limited by the finite bit-length and computational power for decoding. Recently, neural joint source-channel coding (NECST) is proposed to sidestep this problem. While it leverages the advancements of amortized inference and deep learning to improve the encoding and decoding process, it still cannot always achieve compelling results in terms of compression and error correction performance due to the limited robustness of its learned coding networks. In this paper, motivated by the inherent connections between neural joint source-channel coding and discrete representation learning, we propose a novel regularization method called Infomax Adversarial-Bit-Flip (IABF) to improve the stability and robustness of the neural joint source-channel coding scheme. More specifically, on the encoder side, we propose to explicitly maximize the mutual information between the codeword and data; while on the decoder side, the amortized reconstruction is regularized within an adversarial framework. Extensive experiments conducted on various real-world datasets evidence that our IABF can achieve state-of-the-art performances on both compression and error correction benchmarks and outperform the baselines by a significant margin.