DeepCon: Improving Distributed Deep Learning Model Consistency in Edge-Cloud Environments via Distillation

作者：Bin Qian, Jiaxu Qian, Zhenyu Wen, Di Wu, Shibo He, Jiming Chen, Rajiv Ranjan · 发表于：IEEE Transactions on Cognitive Communications and Networking · 年份：2025 · DOI：10.1109/tccn.2025.3547049 · 被引用次数：3 · 研究领域：Cloud Computing and Resource Management、IoT and Edge/Fog Computing

In a typical distributed Deep Learning (DL) based application, models are configured differently to meet the requirements of resource constraints. For instance, a large ResNet56 model is deployed on the cloud server while a small lightweight MobileNet model is more suitable for the end-user device with fewer computation resources. However, the heterogeneity of the model architectures and configurations may bring a systemic problem - models may produce different outputs when given the same input. This inconsistency problem may cause severe system failure of prediction agreement inside the application. Current research has not studied the systemic design for efficiently detecting and reducing the inconsistency among models in distributed DL applications. With the increasing scale of distributed DL applications, the challenges of inconsistency mitigation should consider both algorithm and system design. To this end, we design and implementDeepCon, an adaptive deployment system across the edge-cloud layer with over-the-air model updates. We implement ASRS sampling for efficiently sampling data to reveal the real data distribution as well as model prediction inconsistency. Then, we implement DMML-Par, an asynchronous parallel training algorithm for quickly updating the models and reducing inconsistency.DeepConimplements over-the-air updates with a set of APIS to enable seamless inconsistency detection and reduction in such deep learning applications. Our experiment results on both...