A Flexible Generative Framework for Graph-based Semi-supervised Learning

05/26/2019
by   JiaQi Ma, et al.
0

We consider a family of problems that are concerned about making predictions for the majority of unlabeled, graph-structured data samples based on a small proportion of labeled examples. Relational information among the data samples, often encoded in the graph or network structure, is shown to be helpful for these semi-supervised learning tasks. Conventional graph-based regularization methods and recent graph neural networks do not fully leverage the interrelations between the features, the graph, and the labels. We propose a flexible generative framework for graph-based semi-supervised learning, which approaches the joint distribution of the node features, labels, and the graph structure. Borrowing insights from random graph models in network science literature, this joint distribution can be instantiated using various distribution families. For the inference of missing labels, we exploit recent advances of scalable variational inference techniques to approximate the Bayesian posterior. We conduct thorough experiments on benchmark datasets for graph-based semi-supervised learning. Results show that the proposed methods outperform state-of-the-art models under most settings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/27/2022

Density-Aware Hyper-Graph Neural Networks for Graph-based Semi-supervised Node Classification

Graph-based semi-supervised learning, which can exploit the connectivity...
research
05/25/2023

Jointprop: Joint Semi-supervised Learning for Entity and Relation Extraction with Heterogeneous Graph-based Propagation

Semi-supervised learning has been an important approach to address chall...
research
07/03/2022

Mathematical Foundations of Graph-Based Bayesian Semi-Supervised Learning

In recent decades, science and engineering have been revolutionized by a...
research
08/13/2020

Unifying supervised learning and VAEs – automating statistical inference in high-energy physics

A KL-divergence objective of the joint distribution of data and labels a...
research
12/06/2015

Large Scale Distributed Semi-Supervised Learning Using Streaming Approximation

Traditional graph-based semi-supervised learning (SSL) approaches, even ...
research
02/16/2019

Semi-supervised Learning on Graph with an Alternating Diffusion Process

Graph-based semi-supervised learning usually involves two separate stage...
research
11/05/2018

A Recurrent Graph Neural Network for Multi-Relational Data

The era of data deluge has sparked the interest in graph-based learning ...

Please sign up or login with your details

Forgot password? Click here to reset