Efficient Knowledge Base Synchronization in Semantic Communication Network: A Federated Distillation Approach

Semantic communication powered by artificial intelligence is carried out vigorously to further improve communication efficiency. The knowledge base (KB), as a critical component of semantic communication systems, guides devices to do semantic coding/encoding. However, mismatched KBs hinder semantic alignment between the transceiver and the receiver, which brings severe semantic error. In this work, we design a semantic knowledge base synchronization (SKBS) framework based on federated knowledge distillation for KB establishment and dynamic evolution. In the SKBS, we use the mutual distillation mechanism to learn knowledge from heterogeneous local KBs. Meanwhile, the global KB is compressed to improve the synchronization efficiency. Moreover, a filtering method for KB parameters with noise is applied to mitigate the effects of noise for KB synchronization. The experiment results demonstrate that our proposed approach can assist in establishing a universal global KB and improve the accuracy of multi-user semantic communication while reducing the communication cost during KB synchronization.