Journal article · 2026 · Open access
Efficient and Scalable Multiview Masked Autoencoder for Heterogeneous Graph Self-Supervised Learning
IEEE Transactions on Neural Networks and Learning Systems, PP, 1–15 · Published 30 October 2026 · DOI 10.1109/tnnls.2026.3745261
In brief
“Efficient and Scalable Multiview Masked Autoencoder for Heterogeneous Graph Self-Supervised Learning” is a 2026 journal article by Hao Geng and 7 co-authors, published in IEEE Transactions on Neural Networks and Learning Systems. OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Transactions on Neural Networks and Learning Systems.
- Citations
- 0
- References
- 39
- Authors
- 8
Abstract
Recent years have witnessed the flourishing of self-supervised learning (SSL) on heterogeneous graphs, e.g., masked autoencoder (MAE)-based methods. However, existing MAE-based methods mostly suffer from three issues, including the prohibitive computational cost of constructing meta-path-induced subgraphs, the limitations of uniform random masking, and the suboptimal objective of reconstructing potentially noisy or uninformative original node features. To address these issues, we propose the multiview masked autoencoder (MVMAE)-a novel, efficient, and scalable framework for heterogeneous graph SSL. First, MVMAE introduces a novel multiview mask-then-reconstruct strategy. Instead of masking individual nodes or features, MVMAE randomly masks entire meta-path views and guides the model to reconstruct their representations from remaining visible views. This approach shifts the learning objective to a high-level, semantic task, providing a more robust and informative supervisory signal that is effective even when initial node features are absent or flawed. Then, to handle the computational demands, MVMAE employs an efficient offline aggregation mechanism that precomputes and reuses representations for each meta-path view, completely avoiding the costly construction of meta-path-induced subgraphs. Next, to fuse the representations of each view, MVMAE uses a Transformer-based multiview fusion encoder to capture the complex correlations between views, and a deliberately simple MLP decoder to compel the encoder to learn highly expressive and robust node representations. Extensive experiments on six real-world datasets, including three large-scale graphs, demonstrate that MVMAE consistently outperforms state-of-the-art self-supervised and even semisupervised baselines, confirming its superior effectiveness and scalability. Our source code is released at https://github.com/hcmdgh/MVMAE.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Geng, H., Wang, D., Ge, L., Du, C., Zhuang, F., Yang, B., Hu, Y., & Wang, S. (2026). Efficient and Scalable Multiview Masked Autoencoder for Heterogeneous Graph Self-Supervised Learning. IEEE Transactions on Neural Networks and Learning Systems, PP, 1–15. https://doi.org/10.1109/tnnls.2026.3745261
MLA 9
Geng, Hao, et al. “Efficient and Scalable Multiview Masked Autoencoder for Heterogeneous Graph Self-Supervised Learning.” IEEE Transactions on Neural Networks and Learning Systems, vol. PP, 2026, pp. 1–15. https://doi.org/10.1109/tnnls.2026.3745261.
Chicago
Geng, Hao, Deqing Wang, Lihao Ge, Chenguang Du, Fuzhen Zhuang, Bowen Yang, Yanlin Hu, and Shen Wang. 2026. “Efficient and Scalable Multiview Masked Autoencoder for Heterogeneous Graph Self-Supervised Learning.” IEEE Transactions on Neural Networks and Learning Systems PP: 1–15. https://doi.org/10.1109/tnnls.2026.3745261.
Harvard
Geng, H. et al. (2026) ‘Efficient and Scalable Multiview Masked Autoencoder for Heterogeneous Graph Self-Supervised Learning’, IEEE Transactions on Neural Networks and Learning Systems, PP, pp. 1–15. doi:10.1109/tnnls.2026.3745261.
IEEE
H. Geng et al., “Efficient and Scalable Multiview Masked Autoencoder for Heterogeneous Graph Self-Supervised Learning,” IEEE Transactions on Neural Networks and Learning Systems, vol. PP, pp. 1–15, 2026, doi: 10.1109/tnnls.2026.3745261.
BibTeX
@article{geng2026efficient,
title = {{Efficient and Scalable Multiview Masked Autoencoder for Heterogeneous Graph Self-Supervised Learning}},
author = {Geng, Hao and Wang, Deqing and Ge, Lihao and Du, Chenguang and Zhuang, Fuzhen and Yang, Bowen and Hu, Yanlin and Wang, Shen},
journal = {IEEE Transactions on Neural Networks and Learning Systems},
year = {2026},
volume = {PP},
pages = {1--15},
doi = {10.1109/tnnls.2026.3745261},
url = {https://doi.org/10.1109/tnnls.2026.3745261}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- heterogeneous graphs
- self-supervised learning
- masked autoencoder
- multi-view learning
- multi-view fusion
- node representation learning
- scalability
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Geng, H., Wang, D., Ge, L., Du, C., Zhuang, F., Yang, B., Hu, Y., & Wang, S. (2026). Efficient and Scalable Multiview Masked Autoencoder for Heterogeneous Graph Self-Supervised Learning. IEEE Transactions on Neural Networks and Learning Systems, PP, 1–15. https://doi.org/10.1109/tnnls.2026.3745261
How many times has this paper been cited?
0 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at IEEE Transactions on Neural Networks and Learning Systems: sign in and open the full text from this page.
Who wrote this paper?
Hao Geng, Deqing Wang, Lihao Ge, Chenguang Du, Fuzhen Zhuang, Bowen Yang, Yanlin Hu, Shen Wang.
What is the DOI of this paper?
10.1109/tnnls.2026.3745261, permanently at https://doi.org/10.1109/tnnls.2026.3745261. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.