Adaptive Unequal Error Protection for Semantic Split Learning over Wireless Channels
2026-08-17 • Information Theory
Information Theory
AI summaryⓘ
The authors developed a new method for sending important data from devices to the cloud by focusing more on parts of the data that matter most for the task at hand. They used a special system that learns how to protect these important data parts better during transmission. Their experiments with real sensor data showed that this approach works better than evenly protecting all data, especially when the connection quality changes. They also showed that their method is reliable and can be used for different tasks and datasets.
Semantic split learningWireless edge-cloud inferenceAutoencoderUnequal error protectionMutual informationLatent representationsSignal-to-noise ratioInternet of ThingsGradient sensitivityPhysical layer communication
Authors
Vukan Ninkovic, Dejan Vukobratovic, Dragisa Miskovic, Chao Wang
Abstract
We propose a task-aware semantic split learning (SL) framework for wireless edge-cloud inference, in which the reliability of transmitted latent representations is dynamically adapted to their relevance for the downstream task. An autoencoder (AE)-based physical (PHY) layer enables end-to-end learning of the communication interface, while unequal error protection (UEP) is realized via mutual information (MI)-driven prioritization of latent components during training. The gradient of the estimated MI with respect to each latent component serves as a sensitivity-based proxy for task relevance, providing a fully learning-driven prioritization that adapts to both the data distribution and the downstream task. We further show that this prioritization translates into measurable physical-layer effects: MI-guided UEP assigns significantly higher transmit power to the most task-critical latent components compared to the equal error protection (EEP) baseline. Experiments on real-world IoT sensing data demonstrate consistent gains over equal and fixed-UEP baselines across SNR regimes. Additional analysis confirms ranking stability, estimator robustness and generalization across datasets and task types, indicating broad applicability of the proposed framework.