# InkStream: Real-time GNN Inference on Streaming Graphs via Incremental Update

arXiv: https://arxiv.org/abs/2309.11071 · HTML: https://mlsanity.com/paper/2309.11071/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 45 references that are in the map.
- First posted on arXiv 20 Sep 2023.

## Builds on (most cited first, 27 of 27)

- [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)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [GraphSAINT: Graph Sampling Based Inductive Learning Method](https://mlsanity.com/paper/1907.04931/) (2019)
- [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1905.07953/) (2019)
- [Graph Neural Networks in Recommender Systems: A Survey](https://mlsanity.com/paper/2011.02260/) (2020)
- [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020)
- [EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs](https://mlsanity.com/paper/1902.10191/) (2019)
- [Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking](https://mlsanity.com/paper/1707.03815/) (2017)
- [Graph Neural Network for Traffic Forecasting: A Survey](https://mlsanity.com/paper/2101.11174/) (2021)
- [Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation](https://mlsanity.com/paper/2110.08727/) (2021)
- [AEGNN: Asynchronous Event-based Graph Neural Networks](https://mlsanity.com/paper/2203.17149/) (2022)
- [Streaming Graph Neural Networks](https://mlsanity.com/paper/1810.10627/) (2018)
- [HyGCN: A GCN Accelerator with Hybrid Architecture](https://mlsanity.com/paper/2001.02514/) (2020)
- [Sampling methods for efficient training of graph convolutional networks: A survey](https://mlsanity.com/paper/2103.05872/) (2021)
- [Dynamically Expandable Graph Convolution for Streaming Recommendation](https://mlsanity.com/paper/2303.11700/) (2023)
- [Streaming Recommender Systems](https://mlsanity.com/paper/1607.06182/) (2016)
- [Learning Aggregation Functions](https://mlsanity.com/paper/2012.08482/) (2020)
- [SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Accelerators](https://mlsanity.com/paper/2301.10388/) (2023)

## Built on by (most cited first, 2 of 2)

- [Reforge: Low-Latency Distributed GNN Serving with Selective Embedding Recomputation](https://mlsanity.com/paper/2501.08547/) (2025)
- [TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Information](https://mlsanity.com/paper/2608.30394/) (2026)

## Abstract (arXiv)

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 k-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 principle of propagating and fetching data only when necessary. It uses an event-based system to control inter-layer effect propagation and intra-layer incremental updates of node embedding. InkStream is highly extensible and easily configurable by allowing users to create and process customized events. We showcase that less than 10 lines of additional user code are needed to support popular GNN models such as GCN, GraphSAGE, and GIN. Our experiments with three GNN models on four large graphs demonstrate that InkStream accelerates by 2.5-427× on a CPU cluster and 2.4-343× on two different GPU clusters while producing identical outputs as GNN model inference on the latest graph snapshot.