MULTI-LEVEL APPROACH TO ACCURATE AND SCALABLE HYPERGRAPH EMBEDDING

Sepideh Maleki, Donya Saless, Dennis Wall, Keshav Pingali

Keywords: network embedding, hypergraph embedding, hyperedge classification, multi-level hypergraph embedding

Abstract:

Many problems such as node classification and link prediction in network data
can be solved using graph embeddings, and a number of algorithms are known for constructing
such embeddings. However, it is difficult to use graphs to capture
non-binary relations such as communities of nodes. These kinds of
complex relations are expressed more naturally as hypergraphs.
While hypergraphs are a generalization of graphs, state-of-the-art graph
embedding techniques are not adequate for solving prediction and
classification tasks on large hypergraphs accurately in reasonable time.
In this paper, we introduce NetVec, a novel multi-level framework for scalable unsupervised hypergraph embedding, which outperforms state-of-the-art hypergraph embedding systems by up to
15% in accuracy.
We also show that NetVec is capable of generating high quality embeddings for real-world hypergraphs with millions of nodes and hyperedges in only a couple of minutes while existing hypergraph systems either fail for such large hypergraphs or may take days to produce the embeddings.

One-sentence Summary: In this paper, we introduce NetVec, a novel multi-level framework for scalable unsupervised hypergraph embedding, which outperforms state-of-the-art hypergraph embedding systems by up to 15% in accuracy.