Self-Supervised Contrastive Representation Learning for Semi-Supervised Time-Series Classification
Open accessThe DOI matches its Crossref record; 34 of the 55 references it cites were found in a registry or an index, and 21 are not checked yet; none of the 20 sources its claims cite is checked for support yet.
Abstract
Learning time-series representations when only unlabeled data or few labeled samples are available can be a challenging task. Recently, contrastive self-supervised learning has shown great improvement in extracting useful representations from unlabeled data via contrasting different augmented views of data. In this work, we propose a novel Time-Series representation learning framework via Temporal and Contextual Contrasting (TS-TCC) that learns representations from unlabeled data with contrastive learning. Specifically, we propose time-series-specific weak and strong augmentations and use their views to learn robust temporal relations in the proposed temporal contrasting module, besides learning discriminative representations by our proposed contextual contrasting module. Additionally, we conduct a systematic study of time-series data augmentation selection, which is a key part of contrastive learning. We also extend TS-TCC to the semi-supervised learning settings and propose a Class-Aware TS-TCC (CA-TCC) that benefits from the available few labeled data to further improve representations learned by TS-TCC. Specifically, we leverage the robust pseudo labels produced by TS-TCC to realize a class-aware contrastive loss. Extensive experiments show that the linear evaluation of the features learned by our proposed framework performs comparably with the fully supervised training. Additionally, our framework shows high efficiency in few labeled data and transfer learning scenarios.
Checked 2026-10-05 · 21 references not checked yet
Overview
CoChat Summary
TL;DR
The paper proposes TS-TCC, a self-supervised contrastive framework for time-series representation learning using weak/strong augmentations, temporal contrasting, and contextual contrasting, and extends it to semi-supervised CA-TCC using pseudo-labeled class-aware contrastive learning. Across ten real-world datasets, TS-TCC and CA-TCC outperform self-supervised and semi-supervised baselines under few-label and transfer-learning settings.
Key findings
- With 1% labeled data, TS-TCC achieved the best average linear-evaluation accuracy across 10 datasets: 76.1% vs. 73.3% for CPC, 65.5% for SimCLR, 61.8% for supervised training, and 58.8% for random initialization; with 5% labels, TS-TCC averaged 80.6% vs. 80.0% for CPC and 71.8% for SimCLR.
- CA-TCC’s average F1-score outperformed the second-best semi-supervised baseline by 3.8% and 4.9% with 1% and 5% labels, respectively; its average accuracy was 77.8% at 1% labels and 83.5% at 5% labels.
- In cross-domain fault diagnosis transfer experiments, TS-TCC improved over supervised training by about 4% accuracy on average, and CA-TCC by about 6% accuracy on average.
- Ablation showed the cross-view prediction task improved accuracy by more than 6% on HAR and about 2% on Sleep-EDF and Epilepsy; combining weak and strong augmentations gave the best HAR result at 77.58% accuracy with 5% labels.
Methods
- Design: TS-TCC learns from unlabeled data via time-series-specific weak and strong augmentations, a temporal contrasting module with a tough cross-view prediction task, and a contextual contrasting module. CA-TCC extends this to semi-supervised learning in four phases: TS-TCC pretraining, fine-tuning with few labels, pseudo-label generation, and class-aware supervised contrastive training.
- Data: ten public real-world time-series datasets were used, including UCI HAR, Sleep-EDF, Epilepsy, Fault Diagnosis, and seven UCR datasets (Wafer, FordA, FordB, POC, PPOC, StarLightCurves, ElectricDevices). Experiments used 60%/20%/20% train/validation/test splits, subject-wise split for Sleep-EDF, and 5 runs with different seeds.
- Analysis: performance was measured by accuracy and macro-averaged F1-score, with linear evaluation on frozen pretrained encoders, comparisons against self-supervised and semi-supervised baselines, transfer-learning tests, ablation, sensitivity analysis, and augmentation-selection experiments.
Limitations
- The paper does not include a dedicated limitations section. It states that time-series augmentation selection remains an open problem and that proper augmentation parameters vary by dataset characteristics, requiring normalization and dataset-specific choices.
- The paper notes that ensembling multiple self-supervised algorithms gave only minor improvement while increasing complexity, training time, and computational demands.
- Evident from the text: evaluation is limited to ten datasets and selected label budgets, sensitivity analysis is performed only on HAR, and CA-TCC depends on the quality of pseudo labels generated by the fine-tuned TS-TCC encoder.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 0 Not valid · 12 Not checked · 87 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Experimental results show that both variants are capable of learning effective representations for different scenarios.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Extensive experiments show that the linear evaluation of the features learned by our proposed framework performs comparably with the fully supervised training.”
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Additionally, our framework shows high efficiency in few labeled data and transfer learning scenarios.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Additionally, our framework shows high efficiency in few labeled data and transfer learning scenarios.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We find that the pseudo labels generated by TS-TCC are more accurate than those generated by the other baselines.”
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
59 more claims
Create a free account to see all 99 claims and to verify the 20 references still open.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 14
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?
The cited source says what the claim attributes to it.
In the citing paper
“In the time domain, TS-TCC [116] and its extended version CA-TCC [117] designed two time series data augmentation techniques, one is strong augmentation (permutation-and-jitter), and the other is weak augmentation (jitter-and-scale).”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [117]
The cited source says what the claim attributes to it.
In the citing paper
“TS-TCC [116] and its extended version CA-TCC [117] designed a cross prediction task, which uses the context of x T 1 to predict the target in x T 2 , and vice versa uses the context of x T 2 to predict the target in x T 1 .”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [117]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ 5.1.1 Comparison with Baseline Approaches · p. 8
“| Epilepsy | 75.5 ± 3.6 | 70.5 ± 3.3 | 83.4 ± 0.7 | 80.4 ± 0.7 | 92.8 ± 0.2 | 89.0 ± 0.3 | 92.8 ± 0.3 | 90.2 ± 0.5 | 91.3 ± 0.5 | 89.2 ± 1.0 | 93.1 ± 0.3 | 93.7 ± 0.6 |”
§ 4.1.3 Epilepsy Seizure Prediction · p. 6
“we merged them into one class and treat it as a binary classification problem.”
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
Exploiting 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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Advances in neural information processing systems 7
(1996) · Computers & Mathematics with Applications · doi:10.1016/s0898-1221(96)90463-0 · Cited by 14,281
Momentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347
Representation Learning with Contrastive Predictive Coding
Oord, A. V. D., Li, Y., & Vinyals, O. (2018) · arXiv · doi:10.48550/arxiv.1807.03748 · Cited by 6,242 · cited 4×
“4) CPC [21]: a contrastive self-supervised learning method that predicts future timesteps in the embedding space.”
InfluentialTarvainen, A., & Valpola, H. (2017) · arXiv · doi:10.48550/arxiv.1703.01780 · Cited by 4,275
Exploring Simple Siamese Representation Learning
Chen, X., & He, K. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01549 · Cited by 3,725
Supervised Contrastive Learning
Khosla, P., Teterwak, P., Wang, C., Sarna, A., Tian, Y., Isola, P., Maschinot, A., Liu, C., & Krishnan, D. (2020) · arXiv · doi:10.48550/arxiv.2004.11362 · Cited by 3,569 · cited 2×
“Many studies showed that composing multiple data augmentation operations achieves better performance for image data [4], [43].”
Zhang, R., Isola, P., & Efros, A. A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46487-9_40 · Cited by 3,178
Research works printed but not linked: 3
- 10.5555/3524938.3525087 · doi:10.5555/3524938.3525087
- 10.5555/3495724.3497510 · doi:10.5555/3495724.3497510
- 10.1161/01.cir.101.23.e21 · doi:10.1161/01.cir.101.23.e21
Cited by
Items 201–224 of 224
Lee, H., Jeong, S.-M., Seok, C. L., Park, Y., Kim, S., Kim, J. H., Lee, U. C., Jeong, B. H., & Lee, E. C. (2026) · Electronics · doi:10.3390/electronics15163657
Han, J., Wang, Z., Cao, Z., Xia, S., Gao, W., & Yi, B. (2026) · SPE Journal · doi:10.2118/234697-pa
ConTemPreT: Contextual temporal pre-trained transformer-based forecasting
Midilli, Y. E., & Parshutin, S. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07423-7
BDF: A bilevel data fusion method for classification tasks in IoT applications
Lu, N., Shen, P., Zhao, Q., & Qian, J. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134905
TempoCL: Temporal semi-supervised contrastive learning under open-set and closed-set noisy labels
Liu, J., Yang, K., Yang, S., & Zhou, Y. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116922
He, T., He, Q., Mou, J., & Chen, J. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3729007
GCC-GAN: Graph-Context-Conditioned GAN for Heterogeneous Sensor Dynamic Compensation
Xu, B. Q., Dongyang, X. U., Zhang, W., Tang, H., Wan, J., & Chen, Z. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3728942
Self-citationEntroTS: Entropy-guided representation learning for time series classification
Lin, G., Shen, C., & Wan, L. (2026) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2026.119042
Aymaz, S. (2026) · Karadeniz Fen Bilimleri Dergisi · doi:10.31466/kfbd.1838823
Shang, J., Qiu, H., Gao, L., Jiang, C., & Zio, E. (2026) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2026.114927
Wang, J., Luo, H., Zhang, G., Song, P., Wang, J., Wang, Y., Sun, Z., & Gao, S. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114861
Cross-Modal Self-supervised Learning with Smartphone Records for Early Parkinson’s Disease Detection
He, T., Du, J., & Chen, J. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-3994-8_10
Tang, B., Mao, M., Li, J., & Zhou, F. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114923
Zhou, Y., HAYASHI, N., & Inuiguchi, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7471096
Improving negative generation for self-supervised triplet-based time series classification
Goyo, M. A., Ñanculef, R., & Valle, C. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.117023
Label-Efficient Transferable Learning for Commercial Building Non-Intrusive Load MonitoringPreprint
Zhao, Q., Liu, Q., Wang, S., & Guo, L. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7477835
Unsupervised state-learning for multivariate time series data: a survey and practical guidelines
Overlöper, P. J., Coelho, C., & Niggemann, O. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11704-5
Shao, X., Wang, H., & Wu, Z. (2026) · Sensors · doi:10.3390/s26185891
Tjondronegoro, D., Yuwono, E. I., & Costa, F. D. S. (2026) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-026-03651-6
Adapting Pretrained Large Vision Models for Sensor-based Activity Recognition
Cai, Y.-Z., Feng, R.-X., Cai, K.-L., Liu, Y.-H., Guo, B.-S., & Hong, Z.-Q. (2026) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3832003
AutoResearcHAR: A Multi-Agent Framework for Dataset Adaptive IMU Based Human Activity Recognition
Ray, L. S. S., Rey, V. F., Bian, S., Suh, S., Lukowicz, P., & Zhou, B. (2026) · ACM International Symposium on Wearable Computers (ISWC) · doi:10.1145/3830727.3834823
Cross-Plant Few-Shot Attack Recognition and Detection in Industrial Control Systems
Almansour, M., Ahmad, I. A., & Alassafi, M. O. (2026) · Sensors · doi:10.3390/s26206360
BioDiff: Spectrally consistent diffusion modeling for high-fidelity physiological signal generation
Dai, H., Ding, H., Zhang, Y., Fu, C., Yang, J., Sawan, M., & Zhao, S. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.134824
Metadata
- Authors
- Eldele, E., Ragab, M., Chen, Z., Wu, M., Kwoh, C.-K., Li, X., & Guan, C.
- Affiliations
- Agency for Science, Technology and Research (SG)
- Nanyang Technological University (SG)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2023-12
- Volume
- 45
- Issue
- 12
- Pages
- 15604-15618
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W4386212336
- Cited by
- 224
- References
- 51
- Citations by year
- 2026: 71 · 2025: 89 · 2024: 55 · 2023: 9
- FWCI
- 27.15
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- DR-NTU (Nanyang Technological University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- A*STAR SINGA Scholarship
- Agency for Science, Technology and Research
- AME Programmatic Funds (A20H6b0151)
- Career Development (C210112046)
- MOE Academic Research (MOE2019-T2-2-175)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Keywords
- time series classification, semi-supervised learning, self-supervised learning, contrastive learning, data augmentation, pseudo-labeling, few labeled samples, transfer learning, representation learning
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.
A language model drew the claims from the paper on 2026-10-05, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-05 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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
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.