Conference paper · 2022 · Open access
Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting
International Joint Conference on Artificial Intelligence, 2362–2368 · Published 1 July 2022 · DOI 10.24963/ijcai.2022/328
In brief
“Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting” is a 2022 conference paper by Hongyuan Yu and 6 co-authors, published in International Joint Conference on Artificial Intelligence. OpenAlex counts 104 citations as of 22 November 2026. It is open access: the full text is free to read at International Joint Conference on Artificial Intelligence.
- Citations
- 104
- Most cited in
- 2025 (32)
- Field-weighted impact
- 10.38
- References
- 31
- Authors
- 7
Abstract
Multivariate time-series forecasting is a critical task for many applications, and graph time-series network is widely studied due to its capability to capture the spatial-temporal correlation simultaneously. However, most existing works focus more on learning with the explicit prior graph structure, while ignoring potential information from the implicit graph structure, yielding incomplete structure modeling. Some recent works attempts to learn the intrinsic or implicit graph structure directly, while lacking a way to combine explicit prior structure with implicit structure together. In this paper, we propose Regularized Graph Structure Learning (RGSL) model to incorporate both explicit prior structure and implicit structure together, and learn the forecasting deep networks along with the graph structure. RGSL consists of two innovative modules. First, we derive an implicit dense similarity matrix through node embedding, and learn the sparse graph structure using the Regularized Graph Generation (RGG) based on the Gumbel Softmax trick. Second, we propose a Laplacian Matrix Mixed-up Module (LM3) to fuse the explicit graph and implicit graph together. We conduct experiments on three real-word datasets. Results show that the proposed RGSL model outperforms existing graph forecasting algorithms with a notable margin, while learning meaningful graph structure simultaneously. Our code and models are made publicly available at https://github.com/alipay/RGSL.git.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Yu, H., Li, T., Yu, W., Li, J., Huang, Y., Wang, L., & Liu, A. X. (2022). Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting. International Joint Conference on Artificial Intelligence, 2362–2368. https://doi.org/10.24963/ijcai.2022/328
MLA 9
Yu, Hongyuan, et al. “Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting.” International Joint Conference on Artificial Intelligence, 2022, pp. 2362–2368. https://doi.org/10.24963/ijcai.2022/328.
Chicago
Yu, Hongyuan, Ting Li, Weichen Yu, Jianguo Li, Yan Huang, Liang Wang, and Alex X. Liu. 2022. “Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting.” International Joint Conference on Artificial Intelligence: 2362–2368. https://doi.org/10.24963/ijcai.2022/328.
Harvard
Yu, H. et al. (2022) ‘Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting’, International Joint Conference on Artificial Intelligence, pp. 2362–2368. doi:10.24963/ijcai.2022/328.
IEEE
H. Yu et al., “Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting,” International Joint Conference on Artificial Intelligence, pp. 2362–2368, 2022, doi: 10.24963/ijcai.2022/328.
BibTeX
@inproceedings{yu2022regularized,
title = {{Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting}},
author = {Yu, Hongyuan and Li, Ting and Yu, Weichen and Li, Jianguo and Huang, Yan and Wang, Liang and Liu, Alex X.},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2022},
pages = {2362--2368},
doi = {10.24963/ijcai.2022/328},
url = {https://doi.org/10.24963/ijcai.2022/328}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2022 | 1 | |
| 2023 | 18 | |
| 2024 | 31 | |
| 2025 | 32 | |
| 2026 | 22 |
Its field-weighted citation impact is 10.38: it has been cited 10.38 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- multivariate time series forecasting
- graph structure learning
- node embeddings
- sparse graph learning
- Gumbel-Softmax
- Laplacian matrix
- graph fusion
- semantic knowledge
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?
Yu, H., Li, T., Yu, W., Li, J., Huang, Y., Wang, L., & Liu, A. X. (2022). Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting. International Joint Conference on Artificial Intelligence, 2362–2368. https://doi.org/10.24963/ijcai.2022/328
How many times has this paper been cited?
104 times, according to OpenAlex on 22 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 International Joint Conference on Artificial Intelligence: sign in and open the PDF from this page.
Who wrote this paper?
Hongyuan Yu, Ting Li, Weichen Yu, Jianguo Li, Yan Huang, Liang Wang, Alex X. Liu.
What is the DOI of this paper?
10.24963/ijcai.2022/328, permanently at https://doi.org/10.24963/ijcai.2022/328. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 22 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.