Re:Wide and Deep Learning: Better Together with TensorFlow
by argonaut on Thursday June 30, 2016 @10:55PM
(#12013611)
They (reasonably) claim the joint model doesn't have to be as big, but, for example, it would be interesting the see an ensemble of 2 models: a wide model of the same size as the wide half of the joint model, and a hierarchical model of the same size as the hierarchical half of the joint model.
Another advantage of joint learning (which the authors mentioned) is that the individual models need not be as big when trained independently since they complement each other. Though the joint model will surely be bigger than each of the individual models.