Abstract
In Internet of Things applications, data generated from devices with different characteristics and located at different positions are embedded into different contexts. This poses major challenges for decentralized machine learning as the data distribution across these devices and locations requires consideration for the invariants that characterize them, e.g., in activity recognition applications, the acceleration recorded by hand device must be corrected by the invariant related to the movement of the hand relative to the body. In this article, we propose a new approach that abstracts the exact context surrounding data generators and improves the reconciliation process for decentralized machine learning. Local learners are trained to decompose the learned representations into (i) universal components shared among devices and locations and (ii) local components that capture the specific context of device and location dependencies. The explicit representation of the relative geometry of devices through the special Euclidean Group SE(3) imposes additional constraints that improve the decomposition process. Comprehensive experimental evaluations are carried out on sensor-based activity recognition datasets featuring multi-location and multi-device data collected in a structured sensing environment. Obtained results show the superiority of the proposed method compared with the advanced solutions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aghajan, H., Cavallaro, A.: Multi-camera Networks: Principles and Applications. Academic Press (2009)
Andrew, G., Arora, R., Bilmes, J., Livescu, K.: Deep canonical correlation analysis. In: ICML, pp. 1247–1255. PMLR (2013)
Carollo, J., et al.: Relative phase measures of intersegmental coordination describe motor control impairments in children with cerebral palsy who exhibit stiff-knee gait. Clin. Biomech. 59, 40–46 (2018)
Caselles-Dupré, et al.: Symmetry-based disentangled representation learning requires interaction with environments. In: NeurIPS, vol. 32, pp. 4606–4615 (2019)
Esteves, C., Xu, Y., Allen-Blanchette, C., Daniilidis, K.: Equivariant multi-view networks. In: IEEE/CVF ICCV, pp. 1568–1577 (2019)
Finzi, M., et al.: Generalizing convolutional neural networks for equivariance to lie groups on arbitrary continuous data. In: ICML, pp. 3165–3176 (2020)
Forman, G., Scholz, M.: Apples-to-apples in cross-validation studies. ACM SIGKDD 12(1), 49–57 (2010)
Gjoreski, H., et al.: The university of Sussex-Huawei locomotion and transportation dataset for multimodal analytics with mobile devices. IEEE (2018)
Hamidi, M., Osmani, A.: Data generation process modeling for activity recognition. In: Dong, Y., Mladenić, D., Saunders, C. (eds.) ECML PKDD 2020. LNCS (LNAI), vol. 12460, pp. 374–390. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-67667-4_23
Hamidi, M., Osmani, A.: Human activity recognition: a dynamic inductive bias selection perspective. Sensors 21(21), 7278 (2021)
Hamidi, M., Osmani, A., Alizadeh, P.: A multi-view architecture for the SHL challenge. In: UbiComp-ISWC, pp. 317–322 (2020)
Higgins, I., Amos, D., Pfau, D., Racaniere, S., Matthey, L., et al.: Towards a definition of disentangled representations. arXiv:1812.02230 (2018)
Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., et al.: Beta-VAE: learning basic visual concepts with a constrained variational framework. In: ICLR (2017)
Hsieh, K., Phanishayee, A., Mutlu, O., Gibbons, P.: The non-IID data quagmire of decentralized machine learning. In: ICML, pp. 4387–4398 (2020)
Kairouz, P., et al.: Advances and open problems in federated learning. arXiv:1912.04977 (2019)
Karimireddy, S.P., et al.: SCAFFOLD: stochastic controlled averaging for federated learning. In: ICML, pp. 5132–5143 (2020)
Khaled, A., Mishchenko, K., Richtárik, P.: Tighter theory for local SGD on identical and heterogeneous data. In: AISTATS, pp. 4519–4529 (2020)
Kingma, D., Welling, M.: Auto-encoding variational bayes. arXiv:1312.6114 (2013)
Li, T., Sahu, A.K., Zaheer, M., Sanjabi, M., Talwalkar, A., Smith, V.: Federated optimization in heterogeneous networks. MLSys 2, 429–450 (2020)
Ma, H., Li, W., Zhang, X., Gao, S., Lu, S.: AttnSense: multi-level attention mechanism for multimodal human activity recognition. In: IJCAI, pp. 3109–3115 (2019)
Mathieu, E., Rainforth, T., Siddharth, N., Teh, Y.W.: Disentangling disentanglement in variational autoencoders. In: ICML, pp. 4402–4412 (2019)
McMahan, B., et al.: Communication-efficient learning of deep networks from decentralized data. In: AISTATS, pp. 1273–1282 (2017)
Melendez-Calderon, A., Shirota, C., Balasubramanian, S.: Estimating movement smoothness from inertial measurement units. bioRxiv (2020)
Ordóñez, F.J., Roggen, D.: Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16(1), 115 (2016)
Osmani, A., Hamidi, M.: Reduction of the position bias via multi-level learning for activity recognition. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds.) PAKDD 2022. LNCS, pp. 289–302. Springer, Heidelberg (2022). https://doi.org/10.1007/978-3-031-05936-0_23
Qian, H., et al.: Latent independent excitation for generalizable sensor-based cross-person activity recognition. In: AAAI, vol. 35, pp. 11921–11929 (2021)
Quessard, R., Barrett, T., Clements, W.: Learning disentangled representations and group structure of dynamical environments. In: NeurIPS, vol. 33 (2020)
Shoaib, M., Bosch, S., Incel, O.D., et al.: Fusion of smartphone motion sensors for physical activity recognition. Sensors 14(6), 10146–10176 (2014)
Stisen, A., et al.: Smart devices are different: assessing and mitigatingmobile sensing heterogeneities for activity recognition. In: ACM SenSys, pp. 127–140 (2015)
Dinh, C.T., Tran, N., Nguyen, T.D.: Personalized federated learning with Moreau envelopes. In: NeurIPS, vol. 33 (2020)
Vapnik, V., Izmailov, R.: Complete statistical theory of learning: learning using statistical invariants. In: COPA, pp. 4–40. PMLR (2020)
Vemulapalli, R., Arrate, F., Chellappa, R.: Human action recognition by representing 3D skeletons as points in a lie group. In: IEEE CVPR, pp. 588–595 (2014)
Wu, C., Khalili, A.H., Aghajan, H.: Multiview activity recognition in smart homes with spatio-temporal features. In: ACM/IEEE ICDSC, pp. 142–149 (2010)
Yang, J.Y., et al.: Using acceleration measurements for activity recognition. Pattern Recogn. Lett. 29(16), 2213–2220 (2008)
Yao, S., et al.: DeepSense: a unified deep learning framework for time-series mobile sensing data processing. In: WWW, pp. 351–360 (2017)
Yu, H., et al.: Parallel restarted SGD with faster convergence and less communication. In: AAAI, pp. 5693–5700 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hamidi, M., Osmani, A. (2023). Context Abstraction to Improve Decentralized Machine Learning in Structured Sensing Environments. In: Amini, MR., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2022. Lecture Notes in Computer Science(), vol 13715. Springer, Cham. https://doi.org/10.1007/978-3-031-26409-2_39
Download citation
DOI: https://doi.org/10.1007/978-3-031-26409-2_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26408-5
Online ISBN: 978-3-031-26409-2
eBook Packages: Computer ScienceComputer Science (R0)