An Adaptive Deep Transfer Learning Model for Rumor Detection without Sufficient Identified Rumors

Algorithm 1

Adaptive learning rate update algorithm.

	Require:
	Batch_size ;
	decay rate ;
	weight parameter ;
	gradient parameter ;
	Learning rate ;
	Hyperparameter ;
(1)	initialize parameter ;
(2)	while no convergence do
(3)	Obtain from the last layer.
(4)	Calculate the loss function ;
(5)	Calculate the moving average of uncentered variance over past first-order gradient of the loss function
(6)	Update the learning rate update:
(7)	Calculate the past first-order gradient of weights:
(8)	Update weights of this layer:
(9)	end while