Hyperedge2vec: Distributed Representations for Hyperedges

Anonymous

Nov 07, 2017 (modified: Nov 07, 2017) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: Data structured in form of overlapping or non-overlapping sets is found in a variety of domains, sometimes explicitly but often subtly. For example, teams, which are of prime importance in social science studies are “sets of individuals”; “item sets” in pattern mining are sets; and for various types of analysis in language studies a sentence can be considered as a “set or bag of words”. Although building models and inference algorithms for structured data has been an important task in the fields of machine learning and statistics, research on “set-like” data still remains less explored. Relationships between pairs of elements can be modeled as edges in a graph. However, modeling relationships that involve all members of a set, a hyperedge is a more natural representation for the set. In this work, we focus on the problem of embedding hyperedges in a hypergraph (a network of overlapping sets) to a low dimensional vector space. We present a number of new models, some of which extend existing node-level embedding models to the hyperedge-level, as well as other novel methods that directly work on the hypergraph topology. We propose both probabilistic as well as tensor-based models to leverage the hypergraph structure. Our central focus is to highlight the connection between hypergraphs (topology), tensors (algebra) and probabilistic models. The performance of these models is evaluated with a network of social groups and a network of word phrases. Our results demonstrate the effectiveness of our approach.
  • Keywords: hypergraph, representation learning, tensors

Loading