What is it about?
We propose a novel fine-grained behavior-aware network (BehaviorNet) for dynamic network link prediction. The results show significant performance gains for BehaviorNet over several state-of-the-art (SOTA) discrete dynamic link prediction baselines. Ablation study validates the effectiveness of modeling fine-grained edge and node behaviors.
Featured Image
Photo by GuerrillaBuzz Blockchain PR Agency on Unsplash
Why is it important?
Dynamic link prediction has become a trending research subject because of its wide applications in web, sociology, transportation, and bioinformatics. Currently, the prevailing approach for dynamic link prediction is based on graph neural networks, in which graph representation learning is the key to perform dynamic link prediction tasks. However, there are still great challenges because the structure of graphs evolves over time.
Perspectives
BehaviorNet adapts a transformer-based graph convolution network to capture the latent structural representations of nodes by adding edge behaviors as an additional attribute of edges.
Prof. Tonghua Su
Harbin Institute of Technology
Read the Original
This page is a summary of: BehaviorNet: A Fine-grained Behavior-aware Network for Dynamic Link Prediction, ACM Transactions on the Web, January 2023, ACM (Association for Computing Machinery),
DOI: 10.1145/3580514.
You can read the full text:
Contributors
The following have contributed to this page
