Sequence stacking using dual encoder Seq2Seq recurrent networks

Alessandro Bay, Biswa Sengupta

Oct 31, 2017 (modified: Oct 31, 2017) NIPS 2017 Workshop MLITS Submission readers: everyone
  • Abstract: A widely studied non-polynomial (NP) hard problem lies in finding a route between the two nodes of a graph. Often meta-heuristics algorithms such as $A^{*}$ are employed on graphs with a large number of nodes. Here, we propose a deep recurrent neural network architecture based on the Sequence-2-Sequence model, widely used, for instance in text translation. Particularly, we illustrate that utilising a context vector that has been learned from two different recurrent networks enables increased accuracies in learning the shortest route of a graph. Additionally, we show that one can boost the performance of the Seq2Seq network by smoothing the loss function using a homotopy continuation of the decoder's loss function.
  • Keywords: Recurrent Neural Networks, Ensembling; Seq2Seq