Abstract:
Complex network analysis is difficult and has garnered attention. Representing nodes as low-dimensional dense vectors can help. However, citation and email networks change over time. Most recent embedding methods only embed static networks.
Thus, they ignore critical temporal information, which enhances node embedding. DTINE, an unsupervised deep learning model, uses temporal information to improve node representations in dynamic networks.
We use temporal weight and sampling to extract neighborhood features to preserve network topology. The recurrent neural network will use an attention mechanism to measure historical information and capture network evolution. The proposed method outperforms state-of-the-art methods in four real-world networks.
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
