Deep Hyperedges: a Framework for Transductive and Inductive Learning on Hypergraphs

10/07/2019
by   Josh Payne, et al.
1

From social networks to protein complexes to disease genomes to visual data, hypergraphs are everywhere. However, the scope of research studying deep learning on hypergraphs is still quite sparse and nascent, as there has not yet existed an effective, unified framework for using hyperedge and vertex embeddings jointly in the hypergraph context, despite a large body of prior work that has shown the utility of deep learning over graphs and sets. Building upon these recent advances, we propose Deep Hyperedges (DHE), a modular framework that jointly uses contextual and permutation-invariant vertex membership properties of hyperedges in hypergraphs to perform classification and regression in transductive and inductive learning settings. In our experiments, we use a novel random walk procedure and show that our model achieves and, in most cases, surpasses state-of-the-art performance on benchmark datasets. Additionally, we study our framework's performance on a variety of diverse, non-standard hypergraph datasets and propose several avenues of future work to further enhance DHE.

READ FULL TEXT
research
03/31/2022

Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected Graphs

As a powerful tool for modeling complex relationships, hypergraphs are g...
research
06/19/2023

CAT-Walk: Inductive Hypergraph Learning via Set Walks

Temporal hypergraphs provide a powerful paradigm for modeling time-depen...
research
06/29/2020

Hypergraph Random Walks, Laplacians, and Clustering

We propose a flexible framework for clustering hypergraph-structured dat...
research
05/11/2020

Hypergraph Learning with Line Expansion

Previous hypergraph expansions are solely carried out on either vertex l...
research
06/18/2020

Temporal Graph Networks for Deep Learning on Dynamic Graphs

Graph Neural Networks (GNNs) have recently become increasingly popular d...
research
04/01/2019

MESH: A Flexible Distributed Hypergraph Processing System

With the rapid growth of large online social networks, the ability to an...
research
01/09/2018

Compressing Deep Neural Networks: A New Hashing Pipeline Using Kac's Random Walk Matrices

The popularity of deep learning is increasing by the day. However, despi...

Please sign up or login with your details

Forgot password? Click here to reset