Deploying and executing large model inference on edge devices is challenging due to their limited computational power and memory resources. To address this challenge, we present a novel Split-and-Pipeline, a collaborative inference scheme that partitions a large model into multiple submodels and executes them across distributed edge devices in a pipelined manner. The scheme parallelizes data transfer across multiple CPU cores to avoid transmission bottlenecks. We build a real-world testbed using NVIDIA Jetson series edge devices to demonstrate the proposed scheme, achieving 1.2×–3.0× throughput improvement over state-of-the-art baselines.

In this paper, we propose an efficient model training scheme, namedGroup-basedHierarchicalSplitLearning (GHSL), which can accelerate the artificial intelligence (AI) training process in edge networks in a “first-sequential-then-parallel” manner. Specifically, the proposed scheme hierarchically splits an AI model into a user-side and server-side model, while dividing a number of users into multiple groups. Users in each group train user-side models with the interaction of the shared server-side model sequentially; different groups perform the above training process parallelly; the AI models of each group are aggregated into a global model. We also carry out the convergence analysis for the proposed scheme over non-independent and identically distributed data, which reveals that the convergence rate depends on user grouping. Furthermore, we propose a data-driven two-stage user grouping algorithm to minimize the overall training delay, taking user resource heterogeneity and the black-box training process into account. The proposed algorithm first utilizes the Gaussian process regression approach to determine the number of groups, and then employs the coalition game theory to determine the optimal user grouping decision. Comprehensive simulation results demonstrate that the proposed scheme can reduce training delay, user-side computational workload, and communication overhead by up to 19%, 53%, and 54%, respectively, comparing to state-of-the-art benchmarks.

In this paper, we propose a novel distributed learning scheme, named group-based split federated learning (GSFL), to speed up artificial intelligence (AI) model training. Specifically, the GSFL operates in a split-then-federated manner, which consists of three steps: 1) Model distribution, in which the access point (AP) splits the AI models and distributes the client-side models to clients; 2) Model training, in which each client executes forward propagation and transmit the smashed data to the edge server. The edge server executes forward and backward propagation and then returns the gradient to the clients for updating local client-side models; and 3) Model aggregation, in which edge servers aggregate the server-side and client-side models. Simulation results show that the GSFL outperforms vanilla split learning and federated learning schemes in terms of overall training latency while achieving satisfactory accuracy.