CoChat

Federated Self-Supervised Learning of Multisensor Representations for Embedded Intelligence

Open access
Saeed, Aaqib, Salim, Flora D., Ozcelebi, Tanir, Lukkien, Johan · 2021 · IEEE Internet of Things Journal

The DOI matches its Crossref record; the references it cites are not checked yet.

Abstract

Smartphones, wearables, and Internet-of-Things (IoT) devices produce a wealth of data that cannot be accumulated in a centralized repository for learning supervised models due to privacy, bandwidth limitations, and the prohibitive cost of annotations. Federated learning provides a compelling framework for learning models from decentralized data, but conventionally, it assumes the availability of labeled samples, whereas on-device data are generally either unlabeled or cannot be annotated readily through user interaction. To address these issues, we propose a self-supervised approach termed scalogram-signal correspondence learning based on wavelet transform (WT) to learn useful representations from unlabeled sensor inputs as electroencephalography, blood volume pulse, accelerometer, and WiFi channel-state information. Our auxiliary task requires a deep temporal neural network to determine if a given pair of a signal and its complementary view (i.e., a scalogram generated with WT) align with each other, by optimizing a contrastive objective. We extensively assess the quality of learned features with our multiview strategy on diverse public data sets, achieving strong performance in all domains. We demonstrate the effectiveness of representations learned from an unlabeled input collection on downstream tasks with training a linear classifier over pretrained network, usefulness in low-data regime, transfer learning, and cross-validation. Our methodology achieves competitive performance with fully supervised networks and it works significantly better than pretraining with autoencoders in both central and federated contexts. Notably, it improves the generalization in a semisupervised setting as it reduces the volume of labeled data required through leveraging self-supervised learning.

Overview

Integrity signals

Registry

Crossref · 10.1109/jiot.2020.3009358

Cites

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

The text we found for this paper looks like another document, so its claims and self-check weren’t run. The registry and citation checks still apply.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The text we found for this paper looks like another document, so the self-check wasn’t run.

Citations

The citation lists are queued

They are fetched later and appear here then.

References 42 · Cited by 106

Research works printed but not linked: 16

  1. kone?n?, 2016, Federated learning Strategies for improving communication efficiency
  2. kairouz, 2019, Advances and Open Problems in Federated Learning
  3. oord, 2016, WaveNet A Generative Model for Raw Audio
  4. goodfellow, 2014, Generative adversarial nets, Proc Adv Neural Inf Process Syst, 2672
  5. salakhutdinov, 2009, Deep Boltzmann machines, Proc Artif Intell Stat, 448
  6. merry, 0, Wavelet theory and applications: A literature study, DCT rapporten
  7. oord, 2018, Representation learning with contrastive predictive coding
  8. mcmahan, 2017, Communication-efficient learning of deep networks from decentralized data, Proc Int Conf Artif Intell Statist (AISTATS), 1273
  9. gidaris, 2018, Unsupervised representation learning by predicting image rotations
  10. wang, 2019, Federated evaluation of on-device personalization
  11. zhang, 2015, Deep learning with elastic averaging SGD, Proc Adv Neural Inf Process Syst, 685
  12. balcan, 2012, Distributed learning, communication complexity and privacy, Proc Conf Learn Theory, 26
  13. mikolov, 2013, Distributed representations of words and phrases and their compositionality, Proc Adv Neural Inf Process Syst, 3111
  14. misra, 2019, Mish A Self Regularized Non-Monotonic Neural Activation Function
  15. bonawitz, 2019, Towards Federated Learning at Scale System Design
  16. smith, 2017, Federated multi-task learning, Proc Adv Neural Inf Process Syst, 4424

Metadata

Authors
Saeed, A., Salim, F. D., Ozcelebi, T., & Lukkien, J.
Affiliations
  • Eindhoven University of Technology (NL)
  • RMIT University (AU)
Venue
IEEE Internet of Things Journal
Published
2021-01-15
Volume
8
Issue
2
Pages
1030-1040
ISSN
  • 2327-4662 (ISSN-L)
  • 2372-2541
OpenAlex
W3043229062
Cited by
106
References
42
Citations by year
2026: 15 · 2025: 18 · 2024: 19 · 2023: 20 · 2022: 22 · 2021: 11
FWCI
5.26
Type
journal article
Language
en
Open access
Locations
  • IEEE Internet of Things Journal (publishedVersion)
  • TU/e Research Portal (publishedVersion, other-oa)
  • arXiv (Cornell University) (submittedVersion)
  • RMIT Research Repository (RMIT University Library) (submittedVersion)
  • TU/e Research Portal (submittedVersion, other-oa)
  • arXiv (Cornell University) (cc-by)
Funders
  • SCOTT (www.scott-project.eu) Project
  • Electronic Component Systems for European Leadership Joint Undertaking (737422)
  • European Union’s Horizon 2020 Research and Innovation Programme and Austria, Spain, Finland, Ireland, Sweden, Germany, Poland, Portugal, The Netherlands, Belgium, and Norway
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
Keywords
federated learning, self-supervised learning, wavelet scalogram, contrastive learning, EEG, blood volume pulse, accelerometer, WiFi channel state information, Internet of Things, wearable devices, on-device learning, transfer learning, low-data regimes, semi-supervised learning, temporal neural networks

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: Federated Self-Supervised Learning of Multisensor Representations for Embedded Intelligence. https://app.cochat.ai/papers/10.1109/jiot.2020.3009358
The paper
Saeed, A., Salim, F. D., Ozcelebi, T., & Lukkien, J. (2021). Federated Self-Supervised Learning of Multisensor Representations for Embedded Intelligence. IEEE Internet of Things Journal. https://doi.org/10.1109/jiot.2020.3009358

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.