Knowledge-Aided Federated Learning for Energy-Limited Wireless Networks

Chen, Zhixiong; Yi, Wenqiang; Liu, Yuanwei; Nallanathan, Arumugam

doi:10.1109/tcomm.2023.3261383

Cited by 15 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, due to the statistical and model heterogeneity of personalized semantic encoders, the aggregated semantic centroids of different clients are much diverse even if they are with the same semantic concept. Therefore, dislike other FL frameworks with centroid regularization that achieve the global centroids by simply aggregating the local centroids [11], [12], we design the SCG to generate trainable global semantic centroids F = {F c } C c=1 via contrastive learning. The proposed SCG is constructed by two fully-connected layers with ReLU activation in the middle, and such structure is proven useful in improving the quality of representations [13].…”

Section: B Contrastive Learning-based Scgmentioning

confidence: 99%

Personalized Federated Contrastive Learning

Zhang

Wei

et al. 2022

2022 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

In this letter, we design a federated contrastive learning (FedCL) framework aimed at supporting personalized semantic communication. Our FedCL enables collaborative training of local semantic encoders across multiple clients and a global semantic decoder owned by the base station. This framework supports heterogeneous semantic encoders since it does not require client-side model aggregation. Furthermore, to tackle the semantic imbalance issue arising from heterogeneous datasets across distributed clients, we employ contrastive learning to train a semantic centroid generator (SCG). This generator obtains representative global semantic centroids that exhibit intra-semantic compactness and inter-semantic separability. Consequently, it provides superior supervision for learning discriminative local semantic features. Additionally, we conduct theoretical analysis to quantify the convergence performance of FedCL. Simulation results verify the superiority of the proposed FedCL framework compared to other distributed learning benchmarks in terms of task performance and robustness under different numbers of clients and channel conditions, especially in low signal-to-noise ratio and highly heterogeneous data scenarios.

show abstract

Section: B Contrastive Learning-based Scgmentioning

confidence: 99%