Autoencoder-Based Unequal Error Protection Codes
Vukan Ninkovic, Dejan Vukobratovic, Christian H\"ager, Henk Wymeersch,, Alexandre Graell i Amat

TL;DR
This paper introduces an autoencoder-based method for designing codes with unequal error protection, offering improved performance and flexibility over traditional coding schemes for different importance classes.
Contribution
The paper proposes a novel autoencoder-based framework for UEP code design that generalizes loss functions and demonstrates superior performance compared to existing methods.
Findings
Autoencoder-based UEP codes outperform traditional schemes.
The method provides flexible trade-offs in error protection.
Superior performance in message-wise and bit-wise UEP scenarios.
Abstract
We present a novel autoencoder-based approach for designing codes that provide unequal error protection (UEP) capabilities. The proposed design is based on a generalization of an autoencoder loss function that accommodates both message-wise and bit-wise UEP scenarios. In both scenarios, the generalized loss function can be adjusted using an associated weight vector to trade off error probabilities corresponding to different importance classes. For message-wise UEP, we compare the proposed autoencoder-based UEP codes with a union of random coset codes. For bit-wise UEP, the proposed codes are compared with UEP rateless spinal codes and the superposition of random Gaussian codes. In all cases, the autoencoder-based codes show superior performance while providing design simplicity and flexibility in trading off error protection among different importance classes.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
