HIN2Vec: Explore Meta-paths in Heterogeneous Information Networks for Representation Learning

By Tao-Yang Fu, Wang-Chien Lee, Zhen Lei. International Conference on Information and Knowledge Management, 2017

689 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/9d9d33843d018a77bad7f40da8f27671d29cd776

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

1. Philip S. Yu
2. Chuan Shi
3. Chengqi Zhang
4. Shirui Pan
5. Xiao Wang
6. Charu C. Aggarwal
7. Irwin King
8. Xingquan Zhu

In Statistical and Nonlinear Physics

1. Chuan Shi
2. Xiao Wang
3. Chengqi Zhang
4. Shirui Pan
5. Philip S. Yu
6. Irwin King
7. Xingquan Zhu
8. Jie Yin

Citations in the corpus

• Network Representation Learning: A Survey (2017, background): “[120], [121] have investigated the use of various descriptors (e.”
• Leveraging Meta-path based Context for Top- N Recommendation with A Neural Co-Attention Model (2018, neutral): “al [6] learn node embedding to capture rich relation semantics in HIN via neural network model.”
• Heterogeneous Information Network Embedding for Recommendation (2017, methodology): “[59] utilize a neural network model to capture rich relation semantics inHIN.”
• Graph Learning: A Survey (2021, background): “[110] proposed HIN2Vec, which is a representation learning framework based on meta-paths.”
• A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources (2020, neutral): “[60], [61], [62] and hybrid relation-basedmethods [9], [63].”
• MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding (2020, methodology): “fed to a skip-gram model [19] to generate node embeddings. Given user-defined metapaths, ESim [22] generates node embeddings by learning from sampled positive and negative metapath instances. HIN2vec [11] carries out multiple prediction training tasks to learn representations of nodes and metapaths ”
• Unsupervised Attributed Multiplex Network Embedding (2019, background): “It can be thought of as a special type of heterogeneous network (Dong, Chawla, and Swami 2017; Fu, Lee, and Lei 2017) with a single type of node and multiple types of edges.”
• Heterogeneous Graph Attention Network (2019, background): “HIN2Vec [9] carries out multiple prediction training tasks which learn the latent vectors of nodes and meta-paths simultaneously.”