The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
ACT: Adversarial Convolutional Transformer for Time Series Forecasting
Abstract
Time series forecasting is an important problem involving many fields, including the prediction of extreme weather early warning, electricity consumption planning, and long-term traffic congestion. Compared with one-step-ahead prediction, multi-horizon forecasting demands high prediction capacity of the model. Recent studies have shown the great potential of Transformer to improve the prediction accuracy. However, there are three problems with Transformer that restrict its performance, i.e. error accumulation, short-term and long-term dependencies. First, due to the teacher forcing strategy, the ground truth of target values are given during training and replaced by previous step output during testing. This difference between training and testing can lead to error accumulation. Second, time series data have a strong dependence on their local time information. But in classical Transformer architecture, the dot-product self-attention is computed by point-wise values, which are insensitive to local context. Thus, they may fail to distinguish between a turning point, an outlier and the part of patterns. Third, most methods optimize only one objective function and don't model the distributions of data, which is difficult to capture the long-term intricate patterns of time series. To solve these issues, we propose a Transformer-based time series forecasting model in this paper, named Adversarial Convolutional Transformer(ACT). First, we change the decoding mode from step-by-step wa…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“For example, introducing adversarial training in time series forecasting can improve the accuracy and capture long-term repeated patterns, such as AST [166] and ACT [167].”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [167]
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 2×
“Transformer Recently, Transformer-based methods [19] have achieved great success in series data due to the multi-head self-attention mechanism.”
MethodImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 2×
“CNN-based methods [14]–[16] use multiple layers of causal convolutions to model the data.”
MethodHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“But many RNN-based architectures are hard to train well due to issues with exploding and vanishing gradients, besides the variants of RNNs [11], [12].”
BackgroundAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“Training details Our method contains two networks, which are trained jointly with the ADAM [33] optimizer.”
MethodExploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · cited 1×
“And all the methods are performed in PyTorch [32] three times.”
MethodLabaca-Castro, R. (2023) · Machine Learning under Malware Attack · doi:10.1007/978-3-658-40442-0_9 · Cited by 19,272
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., & Zhang, W. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i12.17325 · Cited by 7,752
Self-citationAn Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
Bai, S., Kolter, J. Z., & Koltun, V. (2018) · arXiv · doi:10.48550/arxiv.1803.01271 · Cited by 4,655 · cited 2×
“CNN-based methods [14]–[16] use multiple layers of causal convolutions to model the data.”
MethodRecent Trends in Deep Learning Based Natural Language Processing [Review Article]
Young, T., Hazarika, D., Poria, S., & Cambria, E. (2018) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2018.2840738 · Cited by 2,921
Research works printed but not linked: 1
- zhu, 2002, Statstream: Statistical monitoring of thousands of data streams in real time, VLDB
Cited by
Deep learning for time series forecasting: a survey
Kong, X., Chen, Z., Liu, W., Ning, K., Zhang, L., Muhammad Marier, S., Liu, Y., Chen, Y., & Xia, F. (2025) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-025-02560-w · Cited by 211
Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects
Zhang, K., Wen, Q., Zhang, C., Cai, R., Jin, M., Liu, Y., Zhang, J. Y., Liang, Y., Pang, G., Song, D., et al. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3387317 · Cited by 295
“For example, introducing adversarial training in time series forecasting can improve the accuracy and capture long-term repeated patterns, such as AST [158] and ACT [159].”
BackgroundHarnessing AI for solar energy: Emergence of transformer models
Hanif, M. F., & Mi, J. (2024) · Applied Energy · doi:10.1016/j.apenergy.2024.123541 · Cited by 64
Saravana, M. K., Roopa, M. S., Arunalatha, J. S., & Venugopal, K. R. (2026) · IEEE Access · doi:10.1109/access.2026.3654408 · Cited by 52
Houssein, E. H., Mohamed, M., Younis, E. M. G., & Mohamed, W. M. (2025) · Journal Of Big Data · doi:10.1186/s40537-025-01318-z · Cited by 45
“The energy sector gains advantages from forecasting for resource planning, using datasets such as electricity transformer temperature [19], solar energy, and electricity consumption [20].”
Metadata
- Authors
- Li, Y., Wang, H., Li, J., Liu, C., & Tan, J.
- Affiliations
- Chinese Academy of Sciences (CN)
- Venue
- 2022 International Joint Conference on Neural Networks (IJCNN)
- Publisher
- IEEE
- Published
- 2022-07-18
- Pages
- 1-8
- ISSN
- 2161-4407 (ISSN-L)
- OpenAlex
- W4312864314
- Cited by
- 19
- References
- 32
- Citations by year
- 2026: 2 · 2025: 6 · 2024: 8 · 2023: 3
- FWCI
- 3.02
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Joint Conference on Neural Networks (IJCNN) (publishedVersion)
- Funders
- National Key Research and Development Program of China (2020YFB1711101)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Social Sciences › Decision Sciences › Management Science and Operations Research › Forecasting Techniques and Applications
- Social Sciences › Transportation › Traffic Prediction and Management Techniques
- Keywords
- time series forecasting, multi-horizon forecasting, adversarial training, convolutional attention, self-attention, error accumulation, teacher forcing, long-range dependencies, local context
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: ACT: Adversarial Convolutional Transformer for Time Series Forecasting. https://app.cochat.ai/papers/10.1109/ijcnn55064.2022.9892791
- The paper
- Li, Y., Wang, H., Li, J., Liu, C., & Tan, J. (2022). ACT: Adversarial Convolutional Transformer for Time Series Forecasting. 2022 International Joint Conference on Neural Networks (IJCNN). https://doi.org/10.1109/ijcnn55064.2022.9892791
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.