Efficient Dynamic Graph Representation Learning at Scale
This addresses scalability issues for dynamic graphs in industrial settings, though it appears incremental as it builds on existing methods with efficiency improvements.
The paper tackled the computational challenges of dynamic graph representation learning for real-world applications like e-commerce and social platforms, proposing the EDGE algorithm that scales to millions of nodes and hundreds of millions of events, achieving new state-of-the-art performance.
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.