ConvDySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention and Convolutional Neural Networks
This work addresses the challenge of efficiently modeling real-world dynamic graphs for applications like link prediction, though it appears incremental as an enhancement of an existing method.
The paper tackled the problem of learning node representations on temporal graphs, which evolve over time, by enhancing DySAT with convolutional neural networks and self-attention. The result showed significant performance gains in single-step link prediction on communication and rating networks compared to state-of-the-art methods.
Learning node representations on temporal graphs is a fundamental step to learn real-word dynamic graphs efficiently. Real-world graphs have the nature of continuously evolving over time, such as changing edges weights, removing and adding nodes and appearing and disappearing of edges, while previous graph representation learning methods focused generally on static graphs. We present ConvDySAT as an enhancement of DySAT, one of the state-of-the-art dynamic methods, by augmenting convolution neural networks with the self-attention mechanism, the employed method in DySAT to express the structural and temporal evolution. We conducted single-step link prediction on a communication network and rating network, Experimental results show significant performance gains for ConvDySAT over various state-of-the-art methods.