Discrete structures play an important role in applications like program language modeling and software engineering.

Neural Information Processing Systems http://nips.cc/

In this article, we attempt to capture the difference between the maximum complexity of deep networks and the complexity of functions that are actually learned (see Figure 1).

Thanks to such progress, there have been growing interests in studying the expressive power of GNNs. One line of work does so by studying their ability to distinguish non-isomorphic graphs.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper presents a method for learning layers of representation and for completing missing queries both in input and labels in single procedure unlike some other methods like deep boltzmann machines (DBM). It is a recurrent net following the same operations as DBM with the goal of predicting a subset of inputs from its complement. Parts of paper are badly written, especially model explanation and multi-inference section, nevertheless the paper should be published and I hope the authors will rewrite them. Details: - The procedure is taken from DBM, however other then that, is there a relation between the DBM and this algorithm, or should we just treat the algorithm as one particular function (recurrent net (RNN)) that predicts subset of inputs from its complement?

Neural Information Processing Systems http://nips.cc/