Federated learning (FL) is one of the popular distributed machine learning (ML) solutions but incurs significant communication and computation costs at edge devices. Federated split learning (FSL) can train sub-models in parallel and reduce the computational burden of edge devices by splitting the model architecture. However, it still requires a high communication overhead due to transmitting the smashed data and gradients between clients and the server in every global round. Furthermore, the server must maintain separate partial models for every client, leading to a significant storage requirement. To address these challenges, this paper proposes a novel communication and storage efficient federated split learning method, termed CSE-FSL, which utilizes an auxiliary network to locally update the weights of the clients while keeping asinglemodel at the server, hence avoiding frequent transmissions of gradients from the server and greatly reducing the storage requirement of the server. Additionally, a new model update method of transmitting the smashed data in selected epochs can reduce the amount of smashed data sent from the clients. We provide a theoretical analysis of CSE-FSL, rigorously guaranteeing its convergence under non-convex loss functions. The extensive experimental results further indicate that CSE-FSL achieves a significant communication reduction over existing FSL solutions using real-world FL tasks.

Wireless federated learning (FL) relies on efficient uplink communications to aggregate model updates across distributed edge devices. Over-the-air computation (a.k.a. AirComp) has emerged as a promising approach for addressing the scala-bility challenge of FL over wireless links with limited communication resources. Unlike conventional methods, AirComp allows multiple edge devices to transmit uplink signals simultaneously, enabling the parameter server to directly decode the average global model. However, existing AirComp solutions are intrinsically analog, while modern wireless systems predominantly adopt digital modulations. Consequently, careful constellation designs are necessary to accurately decode the sum model updates without ambiguity. In this paper, we propose an end-to-end communication system supporting AirComp with digital modulation, aiming to overcome the challenges associated with accurate decoding of the sum signal with constellation designs. We leverage autoencoder network structures and explore the joint optimization of transmitter and receiver components. Our approach fills an important gap in the context of accurately decoding the sum signal in digital modulation-based AirComp, which can advance the deployment of FL in contemporary wireless systems.

Federated learning (FL) is a popular distributed machine learning (ML) paradigm, but is often limited by significant communication costs and edge device computation capabilities. Federated Split Learning (FSL) preserves the parallel model training principle of FL, with a reduced device computation requirement thanks to splitting the ML model between the server and clients. However, FSL still incurs very high communication overhead due to transmitting the smashed data and gradients between the clients and the server in each global round. Furthermore, the server has to maintain separate models for every client, resulting in a significant computation and storage requirement that grows linearly with the number of clients. This paper aims at solving these two issues by proposing a communication and storage efficient federated split learning (CSE-FSL) strategy, which utilizes an auxiliary network to locally update the client models while keeping only a single model at the server, hence avoiding the communication of gradients from the server and greatly reducing the server resource requirement. Communication cost is further reduced by only sending the smashed data in selected epochs from the clients. We provide a rigorous theoretical analysis of CSE-FSL that guarantees its convergence for non-convex loss functions. Extensive experimental results demonstrate that CSE-FSL has a significant communication reduction over existing FSL techniques, while achieving state-of-the-art convergence and model accuracy, using several real-world FL tasks.

Deep fading represents the typical error event when communicating over wireless channels. We show that deep fading is particularly detrimental for federated learning (FL) over wireless communications. In particular, the celebrated FEDAVG and several of its variants break down for FL tasks when deep fading exists in the communication phase. The main contribution of this paper is an optimal global model aggregation method at the parameter server, which allocates different weights to different clients based on not only their learning characteristics but also the instantaneous channel state information at the receiver (CSIR). This is accomplished by first deriving an upper bound on the parallel stochastic gradient descent (SGD) convergence over fading channels, and then solving an optimization problem for the server aggregation weights that minimizes this upper bound. The derived optimal aggregation solution is closed-form, and achieves the well-known O(1/t) convergence rate for strongly-convex loss functions under arbitrary fading and decaying learning rates. We validate our approach using several real-world FL tasks.

Large-volume scientific data is one of the prominent driving forces behind next generation networking. In particular, Software Defined Network (SDN) makes leveraging path-based network multicast services practically feasible. In our prior work, we have developed a cross-layer architecture for supporting reliable file-streams multicasting over SDN-enabled Layer-2 network, and implemented the architecture for a meteorology data distribution application in atmospheric science. However, it is challenging to determine an optimal rate for this application with the varying type, volume, and quality of meteorological data. In this paper, we propose a Quality of Service (QoS)-driven rate management pipeline to determine the optimal rate based on the input traffic characteristics and performance constraints. Specifically, the pipeline employs a feedtype classifier using Multi-Layer Perception (MLP) to recognize the type of meteorological data and a delay prediction regressor using stacked Long Short-Term Memory (LSTM) to predict per-file delay for the file-streams. Finally, we determine the optimal rate for the given file-streams using the trained regressor. We implement this pipeline to test the real-world file-stream data collected from a trial deployment, and the results show that our regressor outperforms all baselines by selecting the optimal rate in the presence of varying file set sizes.