Semantic Proximity Search on Heterogeneous Graph by Proximity Embedding

By Zemin Liu, Vincent Wenchen Zheng, Zhou Zhao, Fanwei Zhu, Kevin Chen-Chuan Chang, Minghui Wu, Jing Ying. 2017

71 citations recorded by the source corpus.

Many real-world networks have a rich collection of objects. The semantics of these objects allows us to capture different classes of proximities, thus enabling an important task of semantic proximity search. As the core of semantic proximity search, we have to measure the proximity on a heterogeneous graph, whose nodes are various types of objects. Most of the existing methods rely on engineering features about the graph structure between two nodes to measure their proximity. With recent development on graph embedding, we see a good chance to avoid feature engineering for semantic proximity search. There is very little work on using graph embedding for semantic proximity search. We also observe that graph embedding methods typically focus on embedding nodes, which is an "indirect'' approach to learn the proximity. Thus, we introduce a new concept of proximity embedding, which directly embeds the network structure between two possibly distant nodes. We also design our proximity embedding, so as to flexibly support both symmetric and asymmetric proximities. Based on the proximity embedding, we can easily estimate the proximity score between two nodes and enable search on the graph. We evaluate our proximity embedding method on three real-world public data sets, and show it outperforms the state-of-the-art baselines.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Statistical and Nonlinear Physics

Citations in the corpus

A Comprehensive Survey of Graph Embedding: Problems, Techniques, and Applications (2017, background): “and edges are not specifically defined [44], [45], [46].”
Subgraph-augmented Path Embedding for Semantic User Search on Heterogeneous Social Network (2018, methodology): “For example, ProxEmbed [20] first samples a number of paths from the query node to the target node, and then uses a recurrent neural network to embed each path as a vector; finally it aggregates multiple path embedding vectors for proximity estimation.”
Distance-Aware DAG Embedding for Proximity Search on Heterogeneous Graphs (2018, unknown): “In this work, we adopt the paths sampling method in (Liu et al. 2017).”
Learning Community Embedding with Community Detection and Node Embedding on Graphs (2017, background): “Graph embedding is the state-of-the-art graph representation framework, which aims to project a graph into a low-dimensional space for further applications [16, 20, 26].”
From Node Embedding To Community Embedding (2016, background): “, 2015] or proximity embedding between two possibly distant nodes in a general heterogeneous graph [Liu et al., 2017].”
A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources (2020, unknown): “Prox [108] uses heterogeneous graph embedding in semantic proximity search.”
Topological Recurrent Neural Network for Diffusion Prediction (2017, unknown): “There is also some graph embedding work that focuses on either edge embedding ( e.g. , TransE [36]), path embedding ( e.g. , ProxEmbed [37]), structure embedding ( e.g. , topoLSTM [38]) or whole graph embedding ( e.g. , Graph Convolutional Network [39]).”
Log2vec: A Heterogeneous Graph Embedding Based Approach for Detecting Cyber Threats within Enterprise (2019, background): “Recently, deep learning is used in graph embedding [28, 45] probably due to its outstanding supervised learning ability.”
Recurrent knowledge graph embedding for effective recommendation (2018, methodology): “We further note that graph embedding based methods have also been applied to other domains, e.g, semantic search [13, 14].”