Network Embedding-Aware Point-of-Interest Recommendation in Location-Based Social Networks

Algorithm 1

The training process of Geo-SRank.

	Require: the user-POI check-in matrix R, learning rate η, regularization parameters , , , , and , the pretrained network embeddings S and T;
	Ensure: the latent factors U, V, X, and Y;
(1)	The initialization of U, V, X, and Y;
(2)	while (L(t) − L() tolerate error) do
(3)	Randomly select one training example from ;
(4)	;
(5)	Calculate by utilizing equation (23);
(6)	Calculate X by utilizing equation (21);
(7)	Calculate by utilizing equation (24);
(8)	Calculate by utilizing equation (25);
(9)	Calculate Y by utilizing equation (22);
(10)	Calculate L(t) (the loss error in t step) by utilizing equation (20);
(11)	end while
(12)	return U, V, X, and Y;