Neural Embedding Propagation on Heterogeneous Networks

09/29/2019
by   Carl Yang, et al.
0

Classification is one of the most important problems in machine learning. To address label scarcity, semi-supervised learning (SSL) has been intensively studied over the past two decades, which mainly leverages data affinity modeled by networks. Label propagation (LP), however, as the most popular SSL technique, mostly only works on homogeneous networks with single-typed simple interactions. In this work, we focus on the more general and powerful heterogeneous networks, which accommodate multi-typed objects and links, and thus endure multi-typed complex interactions. Specifically, we propose neural embedding propagation (NEP), which leverages distributed embeddings to represent objects and dynamically composed modular networks to model their complex interactions. While generalizing LP as a simple instance, NEP is far more powerful in its natural awareness of different types of objects and links, and the ability to automatically capture their important interaction patterns. Further, we develop a series of efficient training strategies for NEP, leading to its easy deployment on real-world heterogeneous networks with millions of objects. With extensive experiments on three datasets, we comprehensively demonstrate the effectiveness, efficiency, and robustness of NEP compared with state-of-the-art network embedding and SSL algorithms.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/18/2018

Semisupervised Learning on Heterogeneous Graphs and its Applications to Facebook News Feed

Graph-based semi-supervised learning is a fundamental machine learning p...
research
11/22/2018

Scalable Label Propagation Algorithms for Heterogeneous Networks

Heterogeneous networks are large graphs consisting of different types of...
research
01/21/2017

Label Propagation on K-partite Graphs with Heterophily

In this paper, for the first time, we study label propagation in heterog...
research
11/07/2021

MetaMIML: Meta Multi-Instance Multi-Label Learning

Multi-Instance Multi-Label learning (MIML) models complex objects (bags)...
research
07/15/2020

Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation

Motivated by the problem relatedness between unsupervised domain adaptat...
research
01/20/2022

Numerical simulation of singularity propagation modeled by linear convection equations with spatially heterogeneous nonlocal interactions

We study the propagation of singularities in solutions of linear convect...
research
04/22/2019

ExplaiNE: An Approach for Explaining Network Embedding-based Link Predictions

Networks are powerful data structures, but are challenging to work with ...

Please sign up or login with your details

Forgot password? Click here to reset