ProGNNosis: A Data-driven Model to Predict GNN Computation Time Using Graph Metrics

TL;DR

ProGNNosis is a data-driven model that predicts GNN training time based on graph metrics, enabling better decision-making for model and acceleration technique selection across diverse graph structures.

Contribution

It introduces a novel regression-based approach to predict GNN computation time from graph features, aiding in optimizing GNN deployment.

Findings

Achieves 1.22X average speedup over random selection.

Effectively predicts GNN training time across multiple models.

Facilitates informed decision-making for graph representation choice.

Abstract

Graph Neural Networks (GNN) show great promise in problems dealing with graph-structured data. One of the unique points of GNNs is their flexibility to adapt to multiple problems, which not only leads to wide applicability, but also poses important challenges when finding the best model or acceleration technique for a particular problem. An example of such challenges resides in the fact that the accuracy or effectiveness of a GNN model or acceleration technique generally depends on the structure of the underlying graph. In this paper, in an attempt to address the problem of graph-dependent acceleration, we propose ProGNNosis, a data-driven model that can predict the GNN training time of a given GNN model running over a graph of arbitrary characteristics by inspecting the input graph metrics. Such prediction is made based on a regression that was previously trained offline using a diverse synthetic graph dataset. In practice, our method allows making informed decisions on which design to use for a specific problem. In the paper, the methodology to build ProGNNosis is defined and applied for a specific use case, where it helps to decide which graph representation is better. Our results show that ProGNNosis helps achieve an average speedup of 1.22X over randomly selecting a graph representation in multiple widely used GNN models such as GCN, GIN, GAT, or GraphSAGE.