Abstract

Many graph analytics problems can be solved via iterative algorithms where the solutions are often characterized by a set of steady-state conditions. Different algorithms respect to different set of f point constraints, so instead of using these tradi tional algorithms, can we learn an algorithm which can obtain the same steady-state solutions automat ically from examples, in an effective and scalable way? How to represent the meta learner for such algorithm and how to carry out the learning? In th paper, we propose an embedding representation for iterative algorithms over graphs, and design a lea ing method which alternates between updating the embeddings and projecting them onto the steadystate constraints. We demonstrate the effectivenes of our framework using a few commonly used graph algorithms, and show that in some cases, the learned algorithm can handle graphs with more than 100,000,000 nodes in a single machine.