Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 324

The DOI matches its Crossref record; 140 of the 140 references it cites were found in a registry or an index.

Heterogeneous Network Representation Learning: A Unified Framework With Survey and Benchmark

Open access
Yang, Carl, Xiao, Yuxin, Zhang, Yu, Sun, Yizhou, Han, Jiawei·2022·IEEE Transactions on Knowledge and Data Engineering

Abstract

Since real-world objects and their interactions are often multi-modal and multi-typed, heterogeneous networks have been widely used as a more powerful, realistic, and generic superclass of traditional homogeneous networks (graphs). Meanwhile, representation learning (a.k.a.embedding) has recently been intensively studied and shown effective for various network mining and analytical tasks. In this work, we aim to provide a unified framework to deeply summarize and evaluate existing research on heterogeneous network embedding (HNE), which includes but goes beyond a normal survey. Since there has already been a broad body of HNE algorithms, as the first contribution of this article, we provide a generic paradigm for the systematic categorization and analysis over the merits of various existing HNE algorithms. Moreover, existing HNE algorithms, though mostly claimed generic, are often evaluated on different datasets. Understandable due to the application favor of HNE, such indirect comparisons largely hinder the proper attribution of improved task performance towards effective data preprocessing and novel technical design, especially considering the various ways possible to construct a heterogeneous network from real-world application data. Therefore, as the second contribution, we create four benchmark datasets with various properties regarding scale, structure, attribute/label availability, andetc. from different sources, towards handy and fair evaluations of HNE algorithms. As the third contribution, we carefully refactor and amend the implementations and create friendly interfaces for 13 popular HNE algorithms, and provide all-around comparisons among them over multiple tasks and experimental settings. By putting all existing HNE algorithms under a unified framework, we aim to provide a universal reference and guideline for the understanding and development of HNE algorithms. Meanwhile, by open-sourcing all data and code, we envision to serve the community with an ready-to-use benchmark platform to test and compare the performance of existing and future HNE algorithms (https://github.com/yangji9181/HNE).

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tkde.2020.3045924

Cites

140 of 140 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 140 references

Research works printed but not linked: 26

  1. 10.1007/978-3-030-04167-0\_33 · DOI · Paper page
  2. 10.1145/1027527.1027531 · doi:10.1145/1027527.1027531
  3. Gilmer, Neural message passing for quantum chemistry, 1263
  4. Bordes, Translating embeddings for modeling multi-relational data, 2787
  5. 10.1145/3308558.3313456 · doi:10.1145/3308558.3313456
  6. Socher, Reasoning with neural tensor networks for knowledge base completion, 926
  7. Chen, FastGCN: Fast learning with graph convolutional networks via importance sampling
  8. Veličković, Deep graph infomax
  9. Niepert, Learning convolutional neural networks for graphs, 2014
  10. 10.5555/3327345.3327389 · doi:10.5555/3327345.3327389
  11. Zhao, Representation learning for measuring entity relatedness with rich information, 1412
  12. Zhou, Learning with local and global consistency, 321
  13. Zhu, Semi-supervised learning using gaussian fields and harmonic functions, 912
  14. 10.1126/science.290.5500–2323 · doi:10.1126/science.290.5500-2323
  15. Vaswani, Attention is all you need, 6000
  16. 10.18653/vl/N19-142 · doi:10.18653/vl/n19-142
  17. Nickel, A three-way model for collective learning on multi-relational data, 809
  18. Fan, LIBLINEAR: A library for large linear classification
  19. Wang, Deep graph library: Towards efficient and scalable deep learning on graphs
  20. Fey, Fast graph representation learning with PyTorch Geometric
  21. You, Position-aware graph neural networks, 7134
  22. Hu, Strategies for pre-training graph neural networks
  23. Bose, Compositional fairness constraints for graph embeddings, 715
  24. Xu, How powerful are graph neural networks?
  25. Sun, InfoGraph: Unsupervised and semi-supervised graph-level representation learning via mutual information maximization
  26. Yang, CubeNet: Multi-facet hierarchical heterogeneous network construction, analysis, and mining

Cited by

See all 324

Metadata

Authors
Yang, C., Xiao, Y., Zhang, Y., Sun, Y., & Han, J.
Venue
IEEE Transactions on Knowledge and Data Engineering
Published
2022-10-01
Volume
34
Issue
10
Pages
4854-4873
ISSN
  • 1041-4347 (ISSN-L)
  • 1558-2191
  • 2326-3865
OpenAlex
W3114303065
Cited by
324
References
140
FWCI
16.95
Type
journal article
Language
en
Open access
green
Funders
  • Army Research Laboratory (W911NF- 09-2-0053, W911NF-13-1-0193)
  • Defense Threat Reduction Agency (HDTRA11810026)
  • Defense Advanced Research Projects Agency (FA8750-19-2-1004, W911NF-17-C-0099)

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Heterogeneous Network Representation Learning: A Unified Framework With Survey and Benchmark. https://app.cochat.ai/papers/10.1109/tkde.2020.3045924
The paper
Yang, C., Xiao, Y., Zhang, Y., Sun, Y., & Han, J. (2022). Heterogeneous Network Representation Learning: A Unified Framework With Survey and Benchmark. IEEE Transactions on Knowledge and Data Engineering. https://doi.org/10.1109/tkde.2020.3045924

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.