Serving Graph Neural Networks With Distributed Fog Servers For Smart IoT Services
This addresses the problem of efficient real-time GNN inference for smart IoT services, offering a domain-specific improvement over existing cloud and fog deployments.
The paper tackles the communication overhead of cloud-based Graph Neural Network (GNN) serving for IoT applications by proposing Fograph, a distributed fog computing framework that achieves up to 5.39x execution speedup and 6.84x throughput improvement compared to state-of-the-art methods.
Graph Neural Networks (GNNs) have gained growing interest in miscellaneous applications owing to their outstanding ability in extracting latent representation on graph structures. To render GNN-based service for IoT-driven smart applications, traditional model serving paradigms usually resort to the cloud by fully uploading geo-distributed input data to remote datacenters. However, our empirical measurements reveal the significant communication overhead of such cloud-based serving and highlight the profound potential in applying the emerging fog computing. To maximize the architectural benefits brought by fog computing, in this paper, we present Fograph, a novel distributed real-time GNN inference framework that leverages diverse and dynamic resources of multiple fog nodes in proximity to IoT data sources. By introducing heterogeneity-aware execution planning and GNN-specific compression techniques, Fograph tailors its design to well accommodate the unique characteristics of GNN serving in fog environments. Prototype-based evaluation and case study demonstrate that Fograph significantly outperforms the state-of-the-art cloud serving and fog deployment by up to 5.39x execution speedup and 6.84x throughput improvement.