Taurus: Accelerating Out-of-Core Graph Neural Network Inference on Billion-Scale Graphs

arXiv:2607.17374v1 Announce Type: cross Abstract: Graph Neural Network (GNN) inference on billion-scale graphs is challenging due to the large memory footprint of features and embeddings and high disk I/O costs in out-of-core settings. Existing distributed GNN systems incur high communication times and infrastructure costs, while disk-based GNN systems are primarily tailored to training and experience massive wasted reads during inference on the entire graph. We present Taurus, a single-machine system for GNN inference on graphs that do not fit in RAM, supporting both \textit{exact} full-graph inference and fanout-sampled inference. To avoid random and repeated feature gathers, Taurus reformulates layer-wise inference as source-centric broadcasts over sequential SSD scans, backed by a pipelined GPU-CPU-SSD hierarchy, topology-aware reordering, pending-message eviction, and a GPU-resident store for high-degree vertices. It further uses non-buffered sequential reads and GPU-backed writes to reduce page-cache pollution, host-memory pressure, and write overheads. On out-of-core graphs with up to $269M$ vertices, $4B$ edges, and $514$ GiB of features, Taurus outperforms the strongest layer-wise baseline, DGI, by $7$-$25\times$, and vertex-wise baselines by $40$-$140\times$.

Abstract:Graph Neural Network (GNN) inference on billion-scale graphs is challenging due to the large memory footprint of features and embeddings and high disk I/O costs in out-of-core settings. Existing distributed GNN systems incur high communication times and infrastructure costs, while disk-based GNN systems are primarily tailored to training and experience massive wasted reads during inference on the entire graph. We present Taurus, a single-machine system for GNN inference on graphs that do not fit in RAM, supporting both \textit{exact} full-graph inference and fanout-sampled inference. To avoid random and repeated feature gathers, Taurus reformulates layer-wise inference as source-centric broadcasts over sequential SSD scans, backed by a pipelined GPU-CPU-SSD hierarchy, topology-aware reordering, pending-message eviction, and a GPU-resident store for high-degree vertices. It further uses non-buffered sequential reads and GPU-backed writes to reduce page-cache pollution, host-memory pressure, and write overheads. On out-of-core graphs with up to $269M$ vertices, $4B$ edges, and $514$ GiB of features, Taurus outperforms the strongest layer-wise baseline, DGI, by $7$-$25\times$, and vertex-wise baselines by $40$-$140\times$.

Extended full-length version of paper that appeared at HPDC 2026: "ATLAS: Efficient Out-of-Core Inference for Billion-Scale Graph Neural Networks", Pranjal Naman and Yogesh Simmhan, in the 35th ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC), 2026. DOI: this https URL

Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG)

arXiv:2607.17374 [cs.DC]

(or arXiv:2607.17374v1 [cs.DC] for this version)

https://doi.org/10.48550/arXiv.2607.17374 arXiv-issued DOI via DataCite (pending registration)

analiza aiqbench

Taurus: Accelerating Out-of-Core Graph Neural Network Inference on Billion-Scale Graphs

Subiecte conexe