Label Propagation with Neural Networks.

Label Propagation (LP) is a popular transductive learning method for very large datasets, in part due to its simplicity and ability to parallelize. However, it has limited ability to handle node features, and its accuracy can be sensitive to the number of iterations. We propose an algorithm called LPNN that solves these problems by a loose-coupling of LP with a feature-based classifier. We experimentally establish the effectiveness of LPNN.