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

arXiv: https://arxiv.org/abs/2607.17374 · HTML: https://mlsanity.com/paper/2607.17374/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 19 Jul 2026.

## Builds on (most cited first, 25 of 25)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters](https://mlsanity.com/paper/2008.08692/) (2020)
- [Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks](https://mlsanity.com/paper/1909.01315/) (2019)
- [AliGraph: A Comprehensive Graph Neural Network Platform](https://mlsanity.com/paper/1902.08730/) (2019)
- [DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs](https://mlsanity.com/paper/2010.05337/) (2020)
- [ETA Prediction with Graph Neural Networks in Google Maps](https://mlsanity.com/paper/2108.11482/) (2021)
- [Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining](https://mlsanity.com/paper/2110.08450/) (2021)
- [IGB: Addressing The Gaps In Labeling, Features, Heterogeneity, and Size of Public Graph Datasets for Deep Learning Research](https://mlsanity.com/paper/2302.13522/) (2023)
- [Ginex: SSD-enabled Billion-scale Graph Neural Network Training on a Single Machine via Provably Optimal In-memory Caching](https://mlsanity.com/paper/2208.09151/) (2022)
- [MariusGNN: Resource-Efficient Out-of-Core Training of Graph Neural Networks](https://mlsanity.com/paper/2202.02365/) (2022)
- [Communication-Efficient Graph Neural Networks with Probabilistic Neighborhood Expansion Analysis and Caching](https://mlsanity.com/paper/2305.03152/) (2023)
- [Accelerating Sampling and Aggregation Operations in GNN Frameworks with GPU Initiated Direct Storage Accesses](https://mlsanity.com/paper/2306.16384/) (2023)
- [DiskGNN: Bridging I/O Efficiency and Model Accuracy for Out-of-Core GNN Training](https://mlsanity.com/paper/2405.05231/) (2024)
- [InferTurbo: A Scalable System for Boosting Full-graph Inference of Graph Neural Network over Huge Graphs](https://mlsanity.com/paper/2307.00228/) (2023)
- [Ripple: Scalable Incremental GNN Inferencing on Large Streaming Graphs](https://mlsanity.com/paper/2505.12112/) (2025)
- [Scaling Real-Time Traffic Analytics on Edge-Cloud Fabrics for City-Scale Camera Networks](https://mlsanity.com/paper/2603.05217/) (2026)
- [Deal: Distributed End-to-End GNN Inference for All Nodes](https://mlsanity.com/paper/2503.02960/) (2025)
- [ATLAS: Efficient Out-of-Core Inference for Billion-Scale Graph Neural Networks](https://mlsanity.com/paper/2605.09402/) (2026)

## Abstract (arXiv)

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 textitexact 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×, and vertex-wise baselines by 40-140×.