feature injection ratio in VPL

[abcsimple]

Since the feature injection ratio is determined by the life indicator T_{y_i} and T_{y_i} is refreshed based on delta t, the feature injection ratio should be adjusted during the training process. However in the table 3 of VPL paper, M_j ratio seems to be a certain value given a delta t. Why is that a certain value in the paper? Any help will be appreciated!