Abstract:
Many node embedding and network representation methods use random walks. However, using traditional random walks results in embeddings that capture proximity (communities) rather than structural similarity (roles). Due to node identity, embeddings cannot be transferred to new nodes and graphs. Role2Vec, based on attributed random walks, learns structural role-based embeddings to overcome these limitations. The framework generalizes any walk-based method. Inductive functions that capture graph structural roles make these methods more widely applicable in the Role2Vec framework. When each vertex is mapped to its unique function, the framework recovers the original methods as a special case. Finally, the Role2Vec framework improves link prediction by 17.8% and uses 853x less space than existing methods on a variety of graphs from different domains.
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
