Graph Neural Networks for Soft Semi-Supervised Learning on Hypergraphs

Naganand Yadati, Tingran Gao, Shahab Asoodeh, Partha Talukdar, Anand Louis

TL;DR: We explore Graph Neural Networks for semi-supervised learning of probability distributions

Abstract:

Graph-based semi-supervised learning (SSL) assigns labels to initially unlabelled vertices in a graph.
Graph neural networks (GNNs), esp. graph convolutional networks (GCNs), inspired the current-state-of-the art models for graph-based SSL problems.
GCNs inherently assume that the labels of interest are numerical or categorical variables.
However, in many real-world applications such as co-authorship networks, recommendation networks, etc., vertex labels can be naturally represented by probability distributions or histograms.
Moreover, real-world network datasets have complex relationships going beyond pairwise associations.
These relationships can be modelled naturally and flexibly by hypergraphs.
In this paper, we explore GNNs for graph-based SSL of histograms.
Motivated by complex relationships (those going beyond pairwise) in real-world networks, we propose a novel method for directed hypergraphs.
Our work builds upon existing works on graph-based SSL of histograms derived from the theory of optimal transportation.
A key contribution of this paper is to establish generalisation error bounds for a one-layer GNN within the framework of algorithmic stability.
We also demonstrate our proposed methods' effectiveness through detailed experimentation on real-world data.
We have made the code available.

Code: https://drive.google.com/file/d/1i7l5jPBPZ3TRG7YkG6NvJ10j19dnAfOf/view?usp=sharing

Keywords: Graph Neural Networks, Soft Semi-supervised Learning, Hypergraphs