No abstract

Federated learning (FL) is a popular framework for training an AI model using distributed mobile data in a wireless network. It features data parallelism by distributing the learning task to multiple edge devices while attempting to preserve their local-data privacy. One main challenge confronting practical FL is that resource constrained devices struggle with the computation intensive task of updating of a deep-neural network model. To tackle the challenge, in this paper, a federated dropout (FedDrop) scheme is proposed building on the classic dropout scheme for random model pruning. Specifically, in each iteration of the FL algorithm, several subnets are independently generated from the global model at the server using dropout but with heterogeneous dropout rates (i.e., parameter-pruning probabilities), each of which is adapted to the state of an assigned channel. The subsets are downloaded to associated devices for updating. Thereby, FdeDrop reduces both the communication overhead and devices' computation loads compared with the conventional FL while outperforming the latter in the case of overfitting and also the FL scheme with uniform dropout (i.e., identical subsets).

No abstract

In this paper, the protograph-based block low density parity check (LDPC) code, which improves the performance and reduces the encoder/decoder complexity than the conventional Digital Video Broadcasting Satellite Second Generation (DVB-S2) LDPC code used for the marine satellite communication, is proposed. The computer simulation results verify that the proposed protograph-based LDPC code has the better performance in both the bit error rate (BER) and the frame error rate (FER) than the conventional DVB-S2 LDPC code.Furthermore, by analyzing the encoding and decoding computational complexity, we show that the protograph-based block LDPC code has the efficient encoder/decoder structure.

Distributed relay scheme for wireless ad hoc multi-hop multicast network composed of low-power and low-complexity wireless devices with high density is proposed. The proposed relay scheme is shown to be better than flooding, which is the distributed relay scheme applied to ZigBee, in the outage probability and the multicast transmission rate by simulations.