mlsanityData to 7 Oct 2026

HeMI: Multi-view Embedding in Heterogeneous Graphs

arXiv 2109.07008 ↗First posted 14 Sep 2021cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Many real-world graphs involve different types of nodes and relations between nodes, being heterogeneous by nature. The representation learning of heterogeneous graphs (HGs) embeds the rich structure and semantics of such graphs into a low-dimensional space and facilitates various data mining tasks, such as node classification, node clustering, and link prediction. In this paper, we propose a self-supervised method that learns HG representations by relying on knowledge exchange and discovery among different HG structural semantics (meta-paths). Specifically, by maximizing the mutual information of meta-path representations, we promote meta-path information fusion and consensus, and ensure that globally shared semantics are encoded. By extensive experiments on node classification, node clustering, and link prediction tasks, we show that the proposed self-supervision both outperforms and improves competing methods by 1% and up to 10% for all tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 26 references that are in the map. First posted on arXiv 14 Sep 2021.

Builds on

21 of 26 references.

References · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  6. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  7. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  8. 2018Deep Graph Infomaxcited by 1,101
  9. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  10. 2019Heterogeneous Graph Attention Networkcited by 732
  11. 2020Contrastive Multi-View Representation Learning on Graphscited by 651
  12. 2015LINE: Large-scale Information Network Embeddingcited by 582
9 more
  1. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  2. 2019Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networkscited by 241
  3. 2017Heterogeneous Information Network Embedding for Recommendationcited by 133
  4. 2019Unsupervised Attributed Multiplex Network Embeddingcited by 95
  5. 2019Heterogeneous Deep Graph Infomaxcited by 42
  6. 2020Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learningcited by 35
  7. 2020Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Propertiescited by 30
  8. 2016Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networkscited by 11
  9. 2020PanRep: Graph neural networks for extracting universal node embeddings in heterogeneous graphscited by 2

Built on by

Not cited yet.