Is a Single Vector Enough? Exploring Node Polysemy for Network Embedding

05/25/2019
by   Ninghao Liu, et al.
0

Networks have been widely used as the data structure for abstracting real-world systems as well as organizing the relations among entities. Network embedding models are powerful tools in mapping nodes in a network into continuous vector-space representations in order to facilitate subsequent tasks such as classification and link prediction. Existing network embedding models comprehensively integrate all information of each node, such as links and attributes, towards a single embedding vector to represent the node's general role in the network. However, a real-world entity could be multifaceted, where it connects to different neighborhoods due to different motives or self-characteristics that are not necessarily correlated. For example, in a movie recommender system, a user may love comedies or horror movies simultaneously, but it is not likely that these two types of movies are mutually close in the embedding space, nor the user embedding vector could be sufficiently close to them at the same time. In this paper, we propose a polysemous embedding approach for modeling multiple facets of nodes, as motivated by the phenomenon of word polysemy in language modeling. Each facet of a node is mapped as an embedding vector, while we also maintain association degree between each pair of node and facet. The proposed method is adaptive to various existing embedding models, without significantly complicating the optimization process. We also discuss how to engage embedding vectors of different facets for inference tasks including classification and link prediction. Experiments on real-world datasets help comprehensively evaluate the performance of the proposed method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/15/2019

Relation Structure-Aware Heterogeneous Information Network Embedding

Heterogeneous information network (HIN) embedding aims to embed multiple...
research
11/02/2022

Hierarchies over Vector Space: Orienting Word and Graph Embeddings

Word and graph embeddings are widely used in deep learning applications....
research
09/11/2022

A Complex Network based Graph Embedding Method for Link Prediction

Graph embedding methods aim at finding useful graph representations by m...
research
11/07/2019

SENSE: Semantically Enhanced Node Sequence Embedding

Effectively capturing graph node sequences in the form of vector embeddi...
research
05/05/2023

Zoo Guide to Network Embedding

Networks have provided extremely successful models of data and complex s...
research
07/18/2021

A Survey on Role-Oriented Network Embedding

Recently, Network Embedding (NE) has become one of the most attractive r...
research
05/19/2018

Conditional Network Embeddings

Network embeddings map the nodes of a given network into d-dimensional E...

Please sign up or login with your details

Forgot password? Click here to reset