Traditionally, the goal of compression is to represent a complex information source such as an image in the most compact way while ensuring an acceptable level of signal distortion. The goal of communication, on the other hand, is to reliably transmit the compressed information over a noisy channel. This talk explored how in-network compression can be used for faster and more reliable communication in 6G networks. This is achieved by task-oriented compression, where instead of minimizing the signal distortion, the goal is to optimize a task described by the wireless network operation. By leveraging recent advances in learning-based data compression, this talk illustrate the potential benefits of learned task-oriented compression for two use cases in 6G. 
The first one is a precoding-oriented Channel State Information (CSI) feedback scheme for multi-cell multi-user MIMO systems, where the learned end-to-end architecture integrates the downlink channel estimation, the CSI compression, and the downlink precoder for higher rates and more effective inference management. The second case is a simple multi-hop network in which a neural detection-oriented relay learns to Compress-and-Forward (CF) its received signal for higher reliability and data rate at the destination. Using a novel machine-learning based distributed compression framework, the first proof-of-concept design for an interpretable and practical neural CF relaying scheme is obtained.