Transferring Learning Trajectories of Neural Networks

Training deep neural networks (DNNs) is computationally expensive, which is problematic especially when performing duplicated training runs, such as model ensemble or knowledge distillation. Once we have trained one DNN on some dataset, we have its learning trajectory (i.e., a sequence of intermediate parameters during training) which may potentially contain useful information for learning the dataset. However, there has been no attempt to utilize such information of a given learning trajectory for another training. In this paper, we formulate the problem of "transferring" a given learning trajectory from one initial parameter to another one, called learning transfer problem, and derive the first algorithm to approximately solve it by matching gradients successively along the trajectory via permutation symmetry. We empirically show that the transferred parameters achieve non-trivial accuracy before any direct training. Also, we analyze the loss landscape property of the transferred parameters, especially from a viewpoint of mode connectivity.