LeL-GNN: Learnable Edge Sampling and Line Based Graph Neural Network for Link Prediction

Graph neural networks lose a lot of their computing power when more network layers are added. As a result, the majority of existing graph neural networks have a shallow depth of learning. Over-smoothing and information loss are two of the key issues that restrict graph neural networks from going dee...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	Md Golam Morshed, Tangina Sultana, Young-Koo Lee
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	IEEE 2023-01-01
Σειρά:	IEEE Access
Θέματα:	Edge sampling deep graph neural networks line graph link prediction
Διαθέσιμο Online:	https://ieeexplore.ieee.org/document/10144318/
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!