Ripple: Scalable Incremental GNN Inferencing on Large Streaming Graphs

TL;DR

Ripple is a scalable framework for real-time incremental GNN inference on large, dynamic graphs, significantly reducing computation and communication costs while maintaining accuracy.

Contribution

Ripple introduces a generalized incremental programming model for efficient, exact GNN update propagation in dynamic graphs, extending to distributed systems.

Findings

Achieves up to 28000 updates/sec on sparse graphs

Provides 30x throughput improvement over baselines

Latency of 0.1ms to 1s suitable for near-realtime applications

Abstract

Most real-world graphs are dynamic in nature, with continuous and rapid updates to the graph topology, and vertex and edge properties. Such frequent updates pose significant challenges for inferencing over Graph Neural Networks (GNNs). Current approaches that perform vertex-wise and layer-wise inferencing are impractical for dynamic graphs as they cause redundant computations, expand to large neighborhoods, and incur high communication costs for distributed setups, resulting in slow update propagation that often exceeds real-time latency requirements. This motivates the need for streaming GNN inference frameworks that are efficient and accurate over large, dynamic graphs. We propose Ripple, a framework that performs fast incremental updates of embeddings arising due to updates to the graph topology or vertex features. Ripple provides a generalized incremental programming model, leveraging the properties of the underlying aggregation functions employed by GNNs to efficiently propagate updates to the affected neighborhood and compute the exact new embeddings. Besides a single-machine design, we also extend this execution model to distributed inferencing, to support large graphs that do not fit in a single machine's memory. Ripple on a single machine achieves up to $\approx28000$ updates/sec for sparse graphs like Arxiv and $\approx1200$ updates/sec for larger and denser graphs like Products, with latencies of $0.1$ms--$1$s that are required for near-realtime applications. The distributed version of Ripple offers up to $\approx30\times$ better throughput over the baselines, due to $70\times$ lower communication costs during updates.