Work

Efficient Dynamic Graph Representation Learning at Scale

Year: 2021

Type: preprint

Abstract: Dynamic graphs with ordered sequences of events between nodes are prevalent in real-world industrial applications such as e-commerce and social platforms. However, representation learning for dynamic graphs has posed great computational challenges due to the time and structure dependency and irregular nature of the data, preventing such models from being deployed to real-world applications. To tackle this challenge, we propose an efficient algorithm, Efficient Dynamic Graph lEarning (EDGE), which selectively expresses certain temporal dependency via training loss to improve the parallelism in computations. We show that EDGE can scale to dynamic graphs with millions of nodes and hundreds of millions of temporal events and achieve new state-of-the-art (SOTA) performance.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2112.07768

Authors: Chen, Xinshi, Zhu, Yan, Xu, Haowen, Liu, Mengyang, Xiong, Liang, Zhang, Muhan, Song, Le

Institutions: Georgia Institute of Technology, Meta (United States), Mohamed bin Zayed University of Artificial Intelligence

Language: English

Topic: Advanced Graph Neural Networks

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4226092302

Cites:

Cited by:

Related to: 10