GNNBENCH: Fair and Productive Benchmarking for Single-GPU GNN System
This provides a fair benchmarking tool for GNN system developers, though it is incremental as it builds on existing system evaluation practices.
The authors tackled the lack of a standardized benchmark for Graph Neural Network (GNN) systems by proposing GNNBench, a plug-and-play platform that identified measurement issues in existing systems.
We hypothesize that the absence of a standardized benchmark has allowed several fundamental pitfalls in GNN System design and evaluation that the community has overlooked. In this work, we propose GNNBench, a plug-and-play benchmarking platform focused on system innovation. GNNBench presents a new protocol to exchange their captive tensor data, supports custom classes in System APIs, and allows automatic integration of the same system module to many deep learning frameworks, such as PyTorch and TensorFlow. To demonstrate the importance of such a benchmark framework, we integrated several GNN systems. Our results show that integration with GNNBench helped us identify several measurement issues that deserve attention from the community.