Integrated Node Encoder for Labelled Textual Networks

05/24/2020
by   Ye Ma, et al.
0

Voluminous works have been implemented to exploit content-enhanced network embedding models, with little focus on the labelled information of nodes. Although TriDNR leverages node labels by treating them as node attributes, it fails to enrich unlabelled node vectors with the labelled information, which leads to the weaker classification result on the test set in comparison to existing unsupervised textual network embedding models. In this study, we design an integrated node encoder (INE) for textual networks which is jointly trained on the structure-based and label-based objectives. As a result, the node encoder preserves the integrated knowledge of not only the network text and structure, but also the labelled information. Furthermore, INE allows the creation of label-enhanced vectors for unlabelled nodes by entering their node contents. Our node embedding achieves state-of-the-art performances in the classification task on two public citation networks, namely Cora and DBLP, pushing benchmarks up by 10.0% and 12.1%, respectively, with the 70% training ratio. Additionally, a feasible solution that generalizes our model from textual networks to a broader range of networks is proposed.

READ FULL TEXT
research
10/10/2016

A General Framework for Content-enhanced Network Representation Learning

This paper investigates the problem of network embedding, which aims at ...
research
11/05/2020

Adversarial Context Aware Network Embeddings for Textual Networks

Representation learning of textual networks poses a significant challeng...
research
06/13/2019

Embedding Biomedical Ontologies by Jointly Encoding Network Structure and Textual Node Descriptors

Network Embedding (NE) methods, which map network nodes to low-dimension...
research
05/15/2017

Active Learning for Graph Embedding

Graph embedding provides an efficient solution for graph analysis by con...
research
11/07/2019

SENSE: Semantically Enhanced Node Sequence Embedding

Effectively capturing graph node sequences in the form of vector embeddi...
research
06/18/2020

Network Together: Node Classification via Cross-Network Deep Network Embedding

Network embedding is a highly effective method to learn low-dimensional ...
research
08/09/2022

E2EG: End-to-End Node Classification Using Graph Topology and Text-based Node Attributes

Node classification utilizing text-based node attributes has many real-w...

Please sign up or login with your details

Forgot password? Click here to reset