# SPEED: Streaming Partition and Parallel Acceleration for Temporal Interaction Graph Embedding

arXiv: https://arxiv.org/abs/2308.14129 · HTML: https://mlsanity.com/paper/2308.14129/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 37 references that are in the map.
- First posted on arXiv 27 Aug 2023.

## Builds on (most cited first, 17 of 17)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1905.07953/) (2019)
- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks](https://mlsanity.com/paper/2101.05974/) (2021)
- [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)
- [DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection](https://mlsanity.com/paper/2207.03579/) (2022)
- [TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs](https://mlsanity.com/paper/2203.14883/) (2022)
- [DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks](https://mlsanity.com/paper/2104.06700/) (2021)
- [Provably expressive temporal graph networks](https://mlsanity.com/paper/2209.15059/) (2022)
- [BGL: GPU-Efficient GNN Training by Optimizing Graph Data I/O and Preprocessing](https://mlsanity.com/paper/2112.08541/) (2021)
- [Learning Optimal Tree Models Under Beam Search](https://mlsanity.com/paper/2006.15408/) (2020)
- [TIGER: Temporal Interaction Graph Embedding with Restarts](https://mlsanity.com/paper/2302.06057/) (2023)
- [Efficient Dynamic Graph Representation Learning at Scale](https://mlsanity.com/paper/2112.07768/) (2021)

## Built on by (most cited first, 7 of 7)

- [A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges](https://mlsanity.com/paper/2405.00476/) (2024)
- [A survey of dynamic graph neural networks](https://mlsanity.com/paper/2404.18211/) (2024)
- [Prompt Learning on Temporal Interaction Graphs](https://mlsanity.com/paper/2402.06326/) (2024)
- [Towards Adaptive Neighborhood for Advancing Temporal Interaction Graph Modeling](https://mlsanity.com/paper/2406.11891/) (2024)
- [Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models](https://mlsanity.com/paper/2503.14411/) (2025)
- [DTFormer: A Transformer-Based Method for Discrete-Time Dynamic Graph Representation Learning](https://mlsanity.com/paper/2407.18523/) (2024)
- [Rethinking Time Encoding via Learnable Transformation Functions](https://mlsanity.com/paper/2505.00887/) (2025)

## Abstract (arXiv)

Temporal Interaction Graphs (TIGs) are widely employed to model intricate real-world systems such as financial systems and social networks. To capture the dynamism and interdependencies of nodes, existing TIG embedding models need to process edges sequentially and chronologically. However, this requirement prevents it from being processed in parallel and struggle to accommodate burgeoning data volumes to GPU. Consequently, many large-scale temporal interaction graphs are confined to CPU processing. Furthermore, a generalized GPU scaling and acceleration approach remains unavailable. To facilitate large-scale TIGs' implementation on GPUs for acceleration, we introduce a novel training approach namely Streaming Edge Partitioning and Parallel Acceleration for Temporal Interaction Graph Embedding (SPEED). The SPEED is comprised of a Streaming Edge Partitioning Component (SEP) which addresses space overhead issue by assigning fewer nodes to each GPU, and a Parallel Acceleration Component (PAC) which enables simultaneous training of different sub-graphs, addressing time overhead issue. Our method can achieve a good balance in computing resources, computing time, and downstream task performance. Empirical validation across 7 real-world datasets demonstrates the potential to expedite training speeds by a factor of up to 19.29x. Simultaneously, resource consumption of a single-GPU can be diminished by up to 69%, thus enabling the multiple GPU-based training and acceleration encompassing millions of nodes and billions of edges. Furthermore, our approach also maintains its competitiveness in downstream tasks.