GNN at the Edge: Cost-Efficient Graph Neural Network Processing over Distributed Edge Servers

by   Liekang Zeng, et al.

Edge intelligence has arisen as a promising computing paradigm for supporting miscellaneous smart applications that rely on machine learning techniques. While the community has extensively investigated multi-tier edge deployment for traditional deep learning models (e.g. CNNs, RNNs), the emerging Graph Neural Networks (GNNs) are still under exploration, presenting a stark disparity to its broad edge adoptions such as traffic flow forecasting and location-based social recommendation. To bridge this gap, this paper formally studies the cost optimization for distributed GNN processing over a multi-tier heterogeneous edge network. We build a comprehensive modeling framework that can capture a variety of different cost factors, based on which we formulate a cost-efficient graph layout optimization problem that is proved to be NP-hard. Instead of trivially applying traditional data placement wisdom, we theoretically reveal the structural property of quadratic submodularity implicated in GNN's unique computing pattern, which motivates our design of an efficient iterative solution exploiting graph cuts. Rigorous analysis shows that it provides parameterized constant approximation ratio, guaranteed convergence, and exact feasibility. To tackle potential graph topological evolution in GNN processing, we further devise an incremental update strategy and an adaptive scheduling algorithm for lightweight dynamic layout optimization. Evaluations with real-world datasets and various GNN benchmarks demonstrate that our approach achieves superior performance over de facto baselines with more than 95.8 eduction in a fast convergence speed.


The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey

Graph Neural Networks (GNNs) are an emerging research field. This specia...

A Comprehensive Survey on Distributed Training of Graph Neural Networks

Graph neural networks (GNNs) have been demonstrated to be a powerful alg...

MAF-GNN: Multi-adaptive Spatiotemporal-flow Graph Neural Network for Traffic Speed Forecasting

Traffic forecasting is a core element of intelligent traffic monitoring ...

Analyzing the Performance of Graph Neural Networks with Pipe Parallelism

Many interesting datasets ubiquitous in machine learning and deep learni...

Staleness-Alleviated Distributed GNN Training via Online Dynamic-Embedding Prediction

Despite the recent success of Graph Neural Networks (GNNs), it remains c...

Optimizing Memory Efficiency of Graph NeuralNetworks on Edge Computing Platforms

Graph neural networks (GNN) have achieved state-of-the-art performance o...

Uncertainty Quantification over Graph with Conformalized Graph Neural Networks

Graph Neural Networks (GNNs) are powerful machine learning prediction mo...

Please sign up or login with your details

Forgot password? Click here to reset