Mining Heterogeneous Information Networks: Principles and Methodologies

By Yizhou Sun, Jiawei Han. Mining Heterogeneous Information Networks: Principles and Methodologies, 2012

553 citations recorded by the source corpus.

Subfields: Information Systems, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/24fafbc64fddff8bad9699343871f5ae5100011e

How researchers see this paper

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

In Information Systems

In Statistical and Nonlinear Physics

Citations in the corpus

Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs (2020, background): “Formally, a network is heterogeneous [34] if it has at least two types of nodes and different relationships between them (e.”
Heterogeneous Graph Transformer (2020, background): “Over the past decade, a significant line of research has been explored for mining heterogeneous graphs [17].”
Are we really making much progress?: Revisiting, benchmarking and refining heterogeneous graph neural networks (2021, methodology): “Meta-paths[29] are proposed to separate different semantics with human prior.”
Large-Scale Embedding Learning in Heterogeneous Event Data (2016, methodology): “Due to the heterogeneity of the objects involved in each event, [13], [21] proposed to abstract such data as heterogeneous information networks.”
Knowledge Graphs (2020, unknown): “A heterogeneous graph [256, 550, 569] (or heterogeneous information network [508, 509]) is a graph where each node and edge is assigned one type.”
Heterogeneous Information Network Embedding for Recommendation (2017, unknown): “Definition 1 (Heterogeneous information network [60]).”
metapath2vec: Scalable Representation Learning for Heterogeneous Networks (2017, methodology): “Previous work has shown that many data mining tasks in heterogeneous information networks can benet from the modeling of meta-paths [6, 25, 27].”
Task-Guided and Path-Augmented Heterogeneous Network Embedding for Author Identification (2016, background): “The bibliographic network can be seen as a heterogeneous network [21].”
Clustering and Community Detection in Directed Networks: A Survey (2013, background): “Finally, heterogeneous networks (in contrast to homogeneous ones) [158], directed or undirected, are used to represent multi-typed networks, i.”
Entity Embedding-Based Anomaly Detection for Heterogeneous Categorical Events (2016, background): “By treating the categorical attributes of an event as entities/nodes, we can also view categorical events as a heterogeneous network of multiple node types [ Sun and Han, 2012 ] .”
GPT-GNN: Generative Pre-Training of Graph Neural Networks (2020, methodology): “Both are widely used heterogeneous graph [30–32].”