Tag2Vec: Learning Tag Representations in Tag Networks

TL;DR

Tag2Vec introduces a novel method for learning rich semantic and hierarchical tag representations by integrating tags into a hybrid network and employing hyperbolic embeddings, improving over existing approaches.

Contribution

The paper presents Tag2Vec, a new model that combines nodes and tags into a hybrid network and uses hyperbolic embeddings to better capture hierarchical structures.

Findings

Outperforms baseline methods on patent and WordNet datasets

Effectively captures semantic and hierarchical tag information

Produces compact, meaningful tag embeddings

Abstract

Network embedding is a method to learn low-dimensional representation vectors for nodes in complex networks. In real networks, nodes may have multiple tags but existing methods ignore the abundant semantic and hierarchical information of tags. This information is useful to many network applications and usually very stable. In this paper, we propose a tag representation learning model, Tag2Vec, which mixes nodes and tags into a hybrid network. Firstly, for tag networks, we define semantic distance as the proximity between tags and design a novel strategy, parameterized random walk, to generate context with semantic and hierarchical information of tags adaptively. Then, we propose hyperbolic Skip-gram model to express the complex hierarchical structure better with lower output dimensions. We evaluate our model on the NBER U.S. patent dataset and WordNet dataset. The results show that our model can learn tag representations with rich semantic information and it outperforms other baselines.