Cache-based GNN System for Dynamic Graphs

Graph Neural Networks (GNNs) have achieved great success in downstream applications due to their ability to learn node representations. However, in many applications, graphs are not static. They often evolve with changes, such as the adjustment of node attributes or graph structures. These changes require node representations to be updated accordingly. It is non-trivial to apply current GNNs to update node representations in a scalable manner. Recent research proposes two types of solutions. The first solution, sampling neighbors for the influenced nodes, requires expensive processing for each node. The second solution, reducing the repeated computations by merging the shared neighbors, cannot speed up the updating process if the influenced nodes do not share neighbors. Most importantly, the above solutions ignore the hidden representations obtained in the previous times that can be reused to accelerate the representation updating. In this paper, we propose a general cache-based GNN system to accelerate the representation updating. Specifically, we cache a set of hidden representations obtained in the previous times, and then reuse them in the next time. To identify valuable hidden representations, we first estimate the number of hidden representations and their combinations that can be reused. Secondly, we formulate the k-assembler problem that selects k representations to maximize the saved time for the next updating process. Experiments on three real-world graphs show that the cache-based GNN system can significantly speed up the representation updating for various GNNs.