ReinDSplit: Reinforced Dynamic Split Learning for Pest Recognition in Precision Agriculture

TL;DR

ReinDSplit introduces a reinforcement learning-based framework that dynamically adjusts split points in distributed neural networks, optimizing resource use and accuracy for pest recognition in precision agriculture.

Contribution

The paper presents ReinDSplit, a novel RL-driven approach that adaptively determines split layers in split learning, addressing heterogeneity in edge devices for improved efficiency and performance.

Findings

Achieves 94.31% accuracy on pest classification datasets.

Effectively balances workloads and latency across heterogeneous devices.

Demonstrates scalability and resource efficiency in agricultural settings.

Abstract

To empower precision agriculture through distributed machine learning (DML), split learning (SL) has emerged as a promising paradigm, partitioning deep neural networks (DNNs) between edge devices and servers to reduce computational burdens and preserve data privacy. However, conventional SL frameworks' one-split-fits-all strategy is a critical limitation in agricultural ecosystems where edge insect monitoring devices exhibit vast heterogeneity in computational power, energy constraints, and connectivity. This leads to straggler bottlenecks, inefficient resource utilization, and compromised model performance. Bridging this gap, we introduce ReinDSplit, a novel reinforcement learning (RL)-driven framework that dynamically tailors DNN split points for each device, optimizing efficiency without sacrificing accuracy. Specifically, a Q-learning agent acts as an adaptive orchestrator, balancing workloads and latency thresholds across devices to mitigate computational starvation or overload. By framing split layer selection as a finite-state Markov decision process, ReinDSplit convergence ensures that highly constrained devices contribute meaningfully to model training over time. Evaluated on three insect classification datasets using ResNet18, GoogleNet, and MobileNetV2, ReinDSplit achieves 94.31% accuracy with MobileNetV2. Beyond agriculture, ReinDSplit pioneers a paradigm shift in SL by harmonizing RL for resource efficiency, privacy, and scalability in heterogeneous environments.