Abstract:
Many fields require network alignment. Many existing works use representation learning without eliminating domain representation bias caused by domain-dependent features, resulting in poor alignment performance. This paper proposes a unified deep architecture (DANA) for domain-invariant network alignment using an adversarial domain classifier. Given a small set of observed anchors, we use graph convolutional networks for domain adversarial network embedding. Maximizing a posterior probability distribution of observed anchors and domain classifier loss optimizes the semi-supervised learning framework. Direction-aware network alignment, weight-sharing for directed networks, and parameter space simplification are some of our model variants. Our approaches achieve state-of-the-art alignment results on three real-world social network datasets.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
