ColloSSL: Collaborative Self-Supervised Learning for Human Activity Recognition
The DOI matches its Crossref record; 58 of the 58 references it cites were found in a registry or an index.
Abstract
A major bottleneck in training robust Human-Activity Recognition models (HAR) is the need for large-scale labeled sensor datasets. Because labeling large amounts of sensor data is an expensive task, unsupervised and semi-supervised learning techniques have emerged that can learn good features from the data without requiring any labels. In this paper, we extend this line of research and present a novel technique called Collaborative Self-Supervised Learning (ColloSSL) which leverages unlabeled data collected from multiple devices worn by a user to learn high-quality features of the data. A key insight that underpins the design of ColloSSL is that unlabeled sensor datasets simultaneously captured by multiple devices can be viewed as natural transformations of each other, and leveraged to generate a supervisory signal for representation learning. We present three technical innovations to extend conventional self-supervised learning algorithms to a multi-device setting: a Device Selection approach which selects positive and negative devices to enable contrastive learning, a Contrastive Sampling algorithm which samples positive and negative examples in a multi-device setting, and a loss function called Multi-view Contrastive Loss which extends standard contrastive loss to a multi-device setting. Our experimental results on three multi-device datasets show that ColloSSL outperforms both fully-supervised and semi-supervised learning techniques in majority of the experiment settings, resulting in an absolute increase of upto 7.9% in F1 score compared to the best performing baselines. We also show that ColloSSL outperforms the fully-supervised methods in a low-data regime, by just using one-tenth of the available labeled data in the best case.
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
“ColloSSL employs a combination of device selection and contrastive sampling algorithms to form training batches from multiple devices, enabling contrastive learning without labeled data.”
From Past, Present, and Future of Sensor-based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task (2025) · cites this paper as [93]
In the citing paper
“ColloSSL (Collaborative Self-Supervised Learning) [93] tackles the scarcity of labeled data in HAR by leveraging time-synchronized data collected from multiple inertial sensors worn by users.”
From Past, Present, and Future of Sensor-based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task (2025) · cites this paper as [93]
In the citing paper
“Leave-one-group-out cross-validation approach is used for performance evaluation follows the previous works [26,34] .”
From Spatial-Temporal Masked Autoencoder for Multi-Device Wearable Human Activity Recognition (2023) · cites this paper as [34]
In the citing paper
“The authors propose ColloSSL, which demonstrates that learning the correlations across multiple devices benefits contrastive learning.”
From Spatial-Temporal Masked Autoencoder for Multi-Device Wearable Human Activity Recognition (2023) · cites this paper as [34]
In the citing paper
“The majority of these works have focused on contrastive approaches [23, 24, 25, 26, 27].”
From Comparing self-supervised learning techniques for wearable human activity recognition (2025) · cites this paper as [27]
Citations
Cites
(2008) · Journal of Machine Learning Research · Cited by 33,051
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
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2019) · arXiv · doi:10.48550/arxiv.1908.09635 · Cited by 5,812
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2022) · ACM Computing Surveys · doi:10.1145/3457607 · Cited by 5,812
Emerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638 · cited 1×
“Self-supervised learning (SSL) has become an increasingly popular area of research in the machine learning community to minimize the reliance on labeled data for training deep learning models [6, 8, 23, 25, 29].”
BackgroundDeep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370 · cited 1×
“For a better interpretability of our findings, we visualize saliency maps [46, 53] for two randomly selected data samples from the RealWorld dataset.”
MethodBootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Grill, J.-B., Strub, F., Altché, F., Tallec, C., Richemond, P. H., Buchatskaya, E., Doersch, C., Pires, B. A., Guo, Z. D., Azar, M. G., et al. (2020) · arXiv · doi:10.48550/arxiv.2006.07733 · Cited by 3,846 · cited 2×
“However, recently novel SSL methods have been proposed which do not require negative samples [10, 17] and outperform contrastive learning methods such as SimCLR.”
BackgroundMethodExploring 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 1×
“Self-supervised learning (SSL) has become an increasingly popular area of research in the machine learning community to minimize the reliance on labeled data for training deep learning models [6, 8, 23, 25, 29].”
BackgroundDeep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Ordóñez, F., & Roggen, D. (2016) · Sensors · doi:10.3390/s16010115 · Cited by 2,761 · cited 1×
“For this purpose, a number of deep learning based sensor fusion techniques [37, 39, 61, 65, 66] have been proposed, which train a fusion model by concatenating multiple sensor streams.”
Research works printed but not linked: 13
- Philip Bachman, R Devon Hjelm, and William Buchwalter. 2019. Learning representations by maximizing mutual information across views. arXiv preprint arXiv:1906.00910 (2019). · arXiv
- Pierre Baldi. 2012. Autoencoders, Unsupervised Learning, and Deep Architectures. In Proceedings of ICML Workshop on Unsupervised and Transfer Learning (Proceedings of Machine Learning Research, Vol. 27), Isabelle Guyon, Gideon Dror, Vincent Lemaire, Graham Taylor, and Daniel Silver (Eds.). PMLR, Bellevue, Washington, USA, 37--49. http://proceedings.mlr.press/v27/baldi12a.html
- Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607.
- Sanorita Dey, Nirupam Roy, Wenyuan Xu, Romit Roy Choudhury, and Srihari Nelakuditi. 2014. AccelPrint: Imperfections of Accelerometers Make Smartphones Trackable.. In NDSS. Citeseer.
- Adam W. Harley, Shrinidhi K. Lakshmikanth, Fangyu Li, Xian Zhou, Hsiao-Yu Fish Tung, and Katerina Fragkiadaki. 2020. Learning from Unlabelled Videos Using Contrastive Predictive Neural 3D Mapping. arXiv:1906.03764 [cs.CV] · arXiv
- Song-Mi Lee, Sang Min Yoon, and Heeryon Cho. 2017. Human activity recognition from accelerometer data using Convolutional Neural Network. In 2017 ieee international conference on big data and smart computing (bigcomp). IEEE, 131--134.
- Daniel S Park, William Chan, Yu Zhang, Chung-Cheng Chiu, Barret Zoph, Ekin D Cubuk, and Quoc V Le. 2019. Specaugment: A simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779 (2019). · arXiv
- Thomas Plötz Nils Y Hammerla and Patrick L Olivier. 2011. Feature learning for activity recognition in ubiquitous computing. In Twenty-second international joint conference on artificial intelligence.
- Charissa Ann Ronao and Sung-Bae Cho. 2016. Human activity recognition with smartphone sensors using deep learning neural networks. Expert systems with applications 59 (2016), 235--244.
- Aaqib Saeed, Victor Ungureanu, and Beat Gfeller. 2020. Sense and Learn: Self-Supervision for Omnipresent Sensors. arXiv preprint arXiv:2009.13233 (2020). · arXiv
- Pritam Sarkar and Ali Etemad. 2020. Self-supervised ecg representation learning for emotion recognition. arXiv preprint arXiv:2002.03898 (2020). · arXiv
- Haizhou Shi, Youcai Zhang, Zijin Shen, Siliang Tang, Yaqian Li, Yandong Guo, and Yueting Zhuang. 2021. Federated Self-Supervised Contrastive Learning via Ensemble Similarity Distillation. arXiv preprint arXiv:2109.14611 (2021). · arXiv
- 10.5555/2832747.2832806 · doi:10.5555/2832747.2832806
Cited by
Self-supervised learning: A succinct review
Rani, V., Nabi, S. T., Kumar, M., Mittal, A., & Kumar, K. (2023) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-023-09884-2 · Cited by 295
Kumar, P., Chauhan, S., & Awasthi, L. K. (2024) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-023-09986-x · Cited by 206
Xiao, Z., Tong, H., Qu, R., Xing, H., Luo, S., Zhu, Z., Song, F., & Feng, L. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3344294 · Cited by 172
Assessing the State of Self-Supervised Human Activity Recognition Using Wearables
Haresamudram, H., Essa, I., & Plötz, T. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3550299 · Cited by 107
COCOA: Cross Modality Contrastive Learning for Sensor Data
Deldari, S., Xue, H., Saeed, A., Smith, D. V., & Salim, F. D. (2022) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3550316 · Cited by 92
Metadata
- Authors
- Jain, Y., Tang, C. I., Min, C., Kawsar, F., & Mathur, A.
- Affiliations
- Georgia Institute of Technology (US)
- University of Cambridge (GB)
- Nokia (United Kingdom) (GB)
- Venue
- Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Published
- 2022-03-29
- Volume
- 6
- Issue
- 1
- Pages
- 1-28
- ISSN
- 2474-9567 (ISSN-L)
- OpenAlex
- W4220693285
- Cited by
- 113
- References
- 46
- Citations by year
- 2026: 16 · 2025: 31 · 2024: 32 · 2023: 29 · 2022: 5
- FWCI
- 7.94
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies (publishedVersion, public-domain)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Keywords
- human activity recognition, unsupervised learning, semi-supervised learning, contrastive learning, device selection, representation learning, wearable sensors, limited labeled data
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
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.