Graph kernels have attracted a lot of attention during the last decade, and have evolved into
a rapidly developing branch of learning on structured data. During the past 20 years, the …

Applications of machine learning methods increasingly deal with graph structured data
through kernels. Most existing graph kernels compare graphs in terms of features defined on …

We develop and apply the Balcan-Blum-Srebro (BBS) theory of classification via similarity
functions (which are not necessarily kernels) to the problem of graph classification. First we …

This paper considers the problem of finding large dense subgraphs in relational graphs, ie,
a set of graphs which share a common vertex set. We present an approximation algorithm …

Given a heterogeneous multilayer network with various connections in pharmacology, how
can we detect components with intensive interactions and strong dependencies? Can we …

Semi-supervised learning on graph structured data has received significant attention with
the recent introduction of Graph Convolution Networks (GCN). While traditional methods …

We study the recently introduced problem of finding dense common subgraphs: Given a
sequence of graphs that share the same vertex set, the goal is to find a subset of vertices $ S …

In this work we design graph neural network architectures that capture optimal
approximation algorithms for a large class of combinatorial optimization problems, using …

Dense subtensor detection gains remarkable success in spotting anomalies and fraudulent
behaviors for multi-aspect data (ie, tensors), like in social media and event streams. Existing …

We introduce a unifying generalization of the Lovász theta function, and the associated
geometric embedding, for graphs with weights on both nodes and edges. We show how it …