InkStream: Real-time GNN Inference on Streaming Graphs via Incremental Update
Dan Wu, Zhaoying Li, Tulika Mitra

TL;DR
InkStream enables real-time GNN inference on streaming graphs by incrementally updating node embeddings, significantly reducing computation and memory access while maintaining identical outputs to traditional static graph methods.
Contribution
The paper introduces InkStream, a novel incremental update method for GNN inference on streaming graphs, improving speed and efficiency over static approaches.
Findings
Achieves 2.5-427× acceleration on CPU clusters.
Achieves 2.4-343× acceleration on GPU clusters.
Maintains identical inference outputs to static GNN methods.
Abstract
Classic Graph Neural Network (GNN) inference approaches, designed for static graphs, are ill-suited for streaming graphs that evolve with time. The dynamism intrinsic to streaming graphs necessitates constant updates, posing unique challenges to acceleration on GPU. We address these challenges based on two key insights: (1) Inside the -hop neighborhood, a significant fraction of the nodes is not impacted by the modified edges when the model uses min or max as aggregation function; (2) When the model weights remain static while the graph structure changes, node embeddings can incrementally evolve over time by computing only the impacted part of the neighborhood. With these insights, we propose a novel method, InkStream, designed for real-time inference with minimal memory access and computation, while ensuring an identical output to conventional methods. InkStream operates on the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Graph Neural Networks · Functional Brain Connectivity Studies · Graph Theory and Algorithms
MethodsGraph Neural Network · Graph Isomorphism Network · Graph Convolutional Network · GraphSAGE
