Enabling Edge Devices that Learn from Each Other: Cross Modal Training for Activity Recognition
Open accessAbstract
Edge devices rely extensively on machine learning for intelligent inferences and pattern matching. However, edge devices use a multitude of sensing modalities and are exposed to wide ranging contexts. It is difficult to develop separate machine learning models for each scenario as manual labeling is not scalable. To reduce the amount of labeled data and to speed up the training process, we propose to transfer knowledge between edge devices by using unlabeled data. Our approach, called RecycleML, uses cross modal transfer to accelerate the learning of edge devices across different sensing modalities. Using human activity recognition as a case study, over our collected CMActivity dataset, we observe that RecycleML reduces the amount of required labeled data by at least 90% and speeds up the training process by up to 50 times in comparison to training the edge device from scratch.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
By using cross-modal transfer in the learning of edge devices across different sensing modalities, required labeled data and the training process can be largely reduced and accelerated, respectively.
“By using the cross-modal transfer in the learning of edge devices across different sensing modalities, required labeled data and the training process can be largely reduced and accelerated, respectively.”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [284]
In order to reduce the amount of training data and speed up the training process, using unlabeled data to transfer knowledge between edge devices can be adopted.
“For instance, in order to reduce the amount of training data and speeding up the training process, using unlabeled data to transfer knowledge between edge devices can be adopted [284].”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [284]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
Distilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204 · see citing works
Advances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653 · see citing works
Learning Spatiotemporal Features with 3D Convolutional Networks
Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.510 · Cited by 9,593 · see citing works
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · see citing works
Large-Scale Machine Learning with Stochastic Gradient Descent
Bottou, L. (2010) · Proceedings of COMPSTAT'2010 · doi:10.1007/978-3-7908-2604-3_16 · Cited by 5,795 · see citing works
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., & Darrell, T. (2013) · arXiv · doi:10.48550/arxiv.1310.1531 · Cited by 4,019 · see citing works
librosa: Audio and Music Signal Analysis in Python
McFee, B., Raffel, C., Liang, D., Ellis, D. P. W., McVicar, M., Battenberg, E., & Nieto, O. (2015) · Proceedings of the Python in Science Conferences · doi:10.25080/majora-7b98e3ed-003 · Cited by 3,099 · see citing works
(2011) · Cited by 2,752 · see citing works
DeViSE: A Deep Visual-Semantic Embedding Model
Frome, A., Corrado, G. S., Shlens, J., Samy Bengio, A., Dean, J., Ranzato, M., & Mikolov, T. (2013) · Cited by 2,309 · see citing works
Internet time synchronization: the network time protocol
Mills, D. L. (1991) · IEEE Transactions on Communications · doi:10.1109/26.103043 · Cited by 1,876 · see citing works
Proceedings of the 29th International Conference on Machine Learning (ICML-12)Preprint
Langford, J. C., & Pineau, J. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1207.4676 · Cited by 1,687 · see citing works
Do Deep Nets Really Need to be Deep?Preprint
Ba, J. L., & Caruana, R. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1312.6184 · Cited by 1,592 · see citing works
(2015) · Cited by 989 · see citing works
Mel Frequency Cepstral Coefficients For Music Modeling.
Logan, B. (2000) · doi:10.5281/zenodo.1416443 · Cited by 928 · see citing works
Neural Information Processing Systems (NIPS)
Shang, X., Zhu, Z., Leimkuhler, B., & Storkey, A. (2015) · Cited by 831 · see citing works
SoundNet: Learning Sound Representations from Unlabeled VideoPreprint
Aytar, Y., Vondrick, C., & Torralba, A. B. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.09001 · Cited by 658 · see citing works
Cross Modal Distillation for Supervision Transfer
Gupta, S., Hoffman, J., & Malik, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.309 · Cited by 530 · see citing works
Music type classification by spectral contrast feature
Jiang, D., Lu, L., Zhang, H.-J., Tao, J., & Cai, L. (2003) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2002.1035731 · Cited by 348 · see citing works
Detecting harmonic change in musical audio
Harte, C. A., Sandler, M. B., & Gasser, M. (2006) · doi:10.1145/1178723.1178727 · Cited by 285 · see citing works
Multimodal Deep Learning for Activity and Context Recognition
Radu, V., Tong, C., Bhattacharya, S., Lane, N. D., Mascolo, C., Marina, M. K., & Kawsar, F. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3161174 · Cited by 281 · see citing works
CNN-based sensor fusion techniques for multimodal human activity recognition
Münzner, S., Schmidt, P., Reiss, A., Hanselmann, M., Stiefelhagen, R., & Dürichen, R. (2017) · ACM International Symposium on Wearable Computers (ISWC) · doi:10.1145/3123021.3123046 · Cited by 236 · see citing works
Audio-visual deep learning for noise robust speech recognition
Huang, J., & Kingsbury, B. E. D. (2013) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2013.6639140 · Cited by 185 · see citing works
Towards multimodal deep learning for activity recognition on mobile devices
Radu, V., Lane, N. D., Bhattacharya, S., Mascolo, C., Marina, M. K., & Kawsar, F. (2016) · Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct · doi:10.1145/2968219.2971461 · Cited by 147 · see citing works
Do Deep Nets Really Need to be DeepPreprint
Ba, L. J., & Caruana, R. (2013) · arXiv (Cornell University) · Cited by 140 · see citing works
Aytar, Y., Castrejón, L., Vondrick, C., Pirsiavash, H., & Torralba, A. B. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2753232 · Cited by 123 · see citing works
MiLift: Efficient Smartwatch-Based Workout Tracking Using Automatic Segmentation
Shen, C., Ho, B.-J., & Srivastava, M. B. (2017) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2017.2775641 · Cited by 69 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2970550 · Cited by 1,498 · see citing works
“For instance, in order to reduce the amount of training data and speeding up the training process, using unlabeled data to transfer knowledge between edge devices can be adopted [284].”
BackgroundMethodBlockchain analytics and artificial intelligence
Dillenberger, D. N., Novotny, P., Zhang, Q., Jayachandran, P., Gupta, H., Hans, S., Verma, D., Chakraborty, S., Thomas, J. J., Walli, M. M., et al. (2019) · IBM Journal of Research and Development · doi:10.1147/jrd.2019.2900638 · Cited by 82 · see citing works
Self-citationDeep Convolutional Bidirectional LSTM for Complex Activity Recognition with Missing Data
Saha, S. S., Sandha, S. S., & Srivastava, M. (2021) · Smart Innovation, Systems and Technologies · doi:10.1007/978-981-15-8269-1_4 · Cited by 12 · see citing works
Self-citation
- Authors
- Xing, T., Sandha, S. S., Balaji, B., Chakraborty, S., & Srivastava, M.
- Affiliations
- University of California, Los Angeles (US)
- IBM Research - Thomas J. Watson Research Center (US)
- Venue
- Proceedings of the 1st International Workshop on Edge Systems, Analytics and Networking
- Publisher
- ACM
- Published
- 2018-06-10
- Pages
- 37-42
- OpenAlex
- W2805572253
- Cited by
- 35
- References
- 27
- Citations by year
- 2026: 1 · 2025: 2 · 2024: 4 · 2023: 3 · 2022: 4 · 2021: 7 · 2020: 7 · 2019: 7
- FWCI
- 2.14
- Type
- conference paper
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- International Workshop on Edge Systems, Analytics and Networking (EdgeSys) (publishedVersion)
- Funders
- Army Research Laboratory (W911NF-16-3-0001)
- National Institutes of Health (#U154EB020404)
- National Science Foundation (#1636916)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Keywords
- edge devices, knowledge transfer, cross-modal transfer, unlabeled data, human activity recognition, sensor fusion, training efficiency
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
