{"ID":2891824,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.16594","arxiv_id":"2507.16594","title":"Optimizing Split Learning Latency in TinyML-Based IoT Systems","abstract":"Split learning (SL) addresses the limitation of running deep learning inference directly on low-power edge/IoT nodes, in which it executes part of the inference process on the sensor and offloading the remainder to a companion device. Despite its promise, the inference latency of SL on constrained hardware under realistic low-power wireless protocols remains unexplored. This paper presents the first experimental latency benchmark of TinyML-based SL on ESP32-S3 boards, comparing four wireless communication protocol solutions (UDP, TCP, ESP-NOW, BLE). We also analyze the impact of the choice of different split points across different models (MobileNet-V2 and ResNet50) in terms of communication and computation overhead as a way to minimize the end-to-end inference latency. We propose a Beam Search-based algorithm for split point optimization that minimizes end-to-end latency, and compare it with other methods, including Greedy Search, First-Fit, Random-Fit, and Brute Force. ESP-NOW achieves the best RTT (3.6 s) and serves as the base protocol for the algorithm, which delivers near-optimal latency with processing time of 0.1 s for 5 devices.","short_abstract":"Split learning (SL) addresses the limitation of running deep learning inference directly on low-power edge/IoT nodes, in which it executes part of the inference process on the sensor and offloading the remainder to a companion device. Despite its promise, the inference latency of SL on constrained hardware under realis...","url_abs":"https://arxiv.org/abs/2507.16594","url_pdf":"https://arxiv.org/pdf/2507.16594v2","authors":"[\"Zied Jenhani\",\"Mounir Bensalem\",\"Jasenka Dizdarević\",\"Admela Jukan\"]","published":"2025-07-22T13:50:12Z","proceeding":"cs.NI","tasks":"[\"cs.NI\",\"cs.AI\",\"cs.DC\"]","methods":"[]","has_code":false}