We consider the two problems of predicting links in a dynamic graph sequence and predicting functions defined at each node of the graph. In many applications, the solution of one problem is useful for solving the other. Indeed, if these functions reflect node features, then they are related through the graph structure. In this paper, we formulate a hybrid approach that simultaneously learns the...

Brain tumor segmentation in magnetic resonance imaging (MRI) is helpful for diagnostics, growth rate prediction, tumor volume measurements and treatment planning of brain tumor. The difficulties for brain tumor segmentation are mainly due to high variation of brain tumors in size, shape, regularity, location, and their heterogeneous appearance (e.g., contrast, intensity and texture variation fo...

We describe a graph-based semi-supervised learning framework in the context of deep neural networks that uses a graph-based entropic regularizer to favor smooth solutions over a graph induced by the data. The main contribution of this work is a computationally efficient, stochastic graph-regularization technique that uses mini-batches that are consistent with the graph structure, but also provi...

Recent literature [1] suggests that embedding a graph on an unit sphere leads to better generalization for graph transduction. However, the choice of optimal embedding and an efficient algorithm to compute the same remains open. In this paper, we show that orthonormal representations, a class of unit-sphere graph embeddings are PAC learnable. Existing PAC-based analysis do not apply as the VC d...

SecDec is a program which can be used for the evaluation of parametric integrals, in particular multi-loop integrals. For a given set of propagators defining the graph, the program constructs the graph polynomials, factorizes the endpoint singularities, and finally produces a Laurent series in the dimensional regularization parameter, whose coefficients are evaluated numerically. In this talk w...

Wikification for tweets aims to automatically identify each concept mention in a tweet and link it to a concept referent in a knowledge base (e.g., Wikipedia). Due to the shortness of a tweet, a collective inference model incorporating global evidence from multiple mentions and concepts is more appropriate than a noncollecitve approach which links each mention at a time. In addition, it is chal...

To understand users’ preference and business performance in terms of customer interest, rating prediction systems are wildly deployed on many social websites. These systems are usually based on the users past history of reviews and similar users. Such traditional recommendation systems suffer from two problems. The first is the cold start problem. In many cases, the system has no knowledge abou...

We propose methods for distributed graph-based multi-task learning that are based on weighted averaging of messages from other machines. Uniform averaging or diminishing stepsize in these methods would yield consensus (single task) learning. We show how simply skewing the averaging weights or controlling the stepsize allows learning different, but related, tasks on the different machines.

We prove certain theoretical properties of a graph-regularized transductive learning objective that is based on minimizing a Kullback-Leibler divergence based loss. These include showing that the iterative alternating minimization procedure used to minimize the objective converges to the correct solution and deriving a test for convergence. We also propose a graph node ordering algorithm that i...

Due to their open and anonymous nature, online social networks are particularly vulnerable to Sybil attacks. In recent years, there has been a rising interest in leveraging social network topological structures to combat Sybil attacks. Unfortunately, due to their strong dependency on unrealistic assumptions, existing graph-based Sybil defense mechanisms suffer from high false detection rates. I...