Machine Learning is an interdisciplinary area dealing with modeling of real-life systems, and robust learning of model parameters. Complex networks deals with real-life networks such as Social Networks, Biological Networks, Computer Networks, etc. which have many non-trivial properties. These two areas have borrowed heavily from each other.
On one hand, techniques in machine learning are used to learn the dynamics of complex networks (link prediction, community formation etc.) as well as learn the dynamics of various functionalities performed on the networks (opinion dynamics, incentive propagation, recommendation, etc.). On the other hand, many machine learning techniques and applications involve systems which learn over graphs/networks, e.g. distributed learning using cluster of machines (distributed regularized loss minimization, distributed convex optimization, distributed recommendation, etc.), learning over graphical models (learning of CRFs, structured learning, etc), deep learning etc.
In this workshop, we are interested in studying the fundamental concepts underlying this area and also discuss the potential research directions and applications.