The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Broadband Analog Aggregation for Low-Latency Federated Edge Learning
Abstract
To leverage rich data distributed at the network edge, a new machine-learning paradigm, called edge learning, has emerged where learning algorithms are deployed at the edge for providing intelligent services to mobile users. While computing speeds are advancing rapidly, the communication latency is becoming the bottleneck of fast edge learning. To address this issue, this work is focused on designing a low-latency multi-access scheme for edge learning. To this end, we consider a popular privacy-preserving framework, federated edge learning (FEEL), where a global AI-model at an edge-server is updated by aggregating (averaging) local models trained at edge devices. It is proposed that the updates simultaneously transmitted by devices over broadband channels should be analog aggregated “over-the-air” by exploiting the waveform-superposition property of a multi-access channel. Such broadband analog aggregation (BAA) results in dramatical communication-latency reduction compared with the conventional orthogonal access (i.e., OFDMA). In this work, the effects of BAA on learning performance are quantified targeting a single-cell random network. First, we derive two tradeoffs between communication-and-learning metrics, which are useful for network planning and optimization. The power control (“truncated channel inversion”) required for BAA results in a tradeoff between the update-reliability [as measured by the receive signal-to-noise ratio (SNR)] and the expected update-truncation ratio. Consider the scheduling of cell-interior devices to constrain path loss. This gives rise to the other tradeoff between the receive SNR and fraction of data exploited in learning. Next, the latency-reduction ratio of the proposed BAA with respect to the traditional OFDMA scheme is proved to scale almost linearly with the device population. Experiments based on a neural network and a real dataset are conducted for corroborating the theoretical results.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A Survey on Mobile Edge Computing: The Communication Perspective
Mao, Y., You, C., Zhang, J., Huang, K., & Letaief, K. B. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2745201 · Cited by 5,607
Self-citationA survey of mobility models for ad hoc network research
Camp, T., Boleng, J., & Davies, V. (2002) · Wireless Communications and Mobile Computing · doi:10.1002/wcm.72 · Cited by 4,621
Federated Learning: Strategies for Improving Communication Efficiency
Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016) · arXiv · doi:10.48550/arxiv.1610.05492 · Cited by 3,766
Mobility increases the capacity of ad hoc wireless networks
Grossglauser, M., & Tse, D. N. C. (2002) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2002.801403 · Cited by 2,839
Variable-rate variable-power MQAM for fading channels
Goldsmith, A. J., & Chua, S.-G. (1997) · IEEE Transactions on Communications · doi:10.1109/26.634685 · Cited by 2,296
Computation Over Multiple-Access Channels
Nazer, B., & Gastpar, M. (2007) · IEEE Transactions on Information Theory · doi:10.1109/tit.2007.904785 · Cited by 753
Sparse Communication for Distributed Gradient Descent
Aji, A. F., & Heafield, K. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1045 · Cited by 585
Narrow Band Internet of Things
Chen, M., Miao, Y., Hao, Y., & Hwang, K. (2017) · IEEE Access · doi:10.1109/access.2017.2751586 · Cited by 458
Communication-Efficient Distributed Statistical Inference
Jordan, M. I., Lee, J. D., & Yang, Y. (2019) · Journal of the American Statistical Association · doi:10.1080/01621459.2018.1429274 · Cited by 442
Uncoded Transmission Is Exactly Optimal for a Simple Gaussian “Sensor” Network
Gastpar, M. (2008) · IEEE Transactions on Information Theory · doi:10.1109/tit.2008.929967 · Cited by 317
Rate Region of the Quadratic Gaussian Two-Encoder Source-Coding Problem
Wagner, A. B., Tavildar, S., & Viswanath, P. (2008) · IEEE Transactions on Information Theory · doi:10.1109/tit.2008.920343 · Cited by 299
Linear Coherent Decentralized Estimation
Xiao, J.-J., Cui, S., Luo, Z.-Q., & Goldsmith, A. J. (2008) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2007.906762 · Cited by 277
MIMO Over-the-Air Computation for High-Mobility Multimodal Sensing
Zhu, G., & Huang, K. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2871070 · Cited by 273
Self-citationWhen Edge Meets Learning: Adaptive Control for Resource-Constrained Distributed Machine Learning
Wang, S., Tuor, T., Salonidis, T., Leung, K. K., Makaya, C., He, T., & Chan, K. (2018) · IEEE INFOCOM 2018 - IEEE Conference on Computer Communications · doi:10.1109/infocom.2018.8486403 · Cited by 209
Robust Analog Function Computation via Wireless Multiple-Access Channels
Goldenbaum, M., & Stanczak, S. (2013) · IEEE Transactions on Communications · doi:10.1109/tcomm.2013.072913.120815 · Cited by 187
AirShare: Distributed coherent transmission made seamless
Abari, O., Rahul, H., Katabi, D., & Pant, M. (2015) · 2015 IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom.2015.7218555 · Cited by 170
Li, X., Zhu, G., Gong, Y., & Huang, K. (2019) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2914046 · Cited by 143
Self-citationOver-the-air Function Computation in Sensor Networks
Abari, O., Rahul, H., & Katabi, D. (2016) · arXiv · doi:10.48550/arxiv.1612.02307 · Cited by 114
Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air
Amiri, M. M., & Gündüz, D. (2019) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2019.8849334 · Cited by 114
Wen, D., Zhu, G., & Huang, K. (2019) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2934956 · Cited by 99
Self-citationOn the Channel Estimation Effort for Analog Computation over Wireless Multiple-Access Channels
Goldenbaum, M., & Stańczak, S. (2014) · IEEE Wireless Communications Letters · doi:10.1109/wcl.2014.022314.140005 · Cited by 58
Communicating Linear Functions of Correlated Gaussian Sources Over a MAC
Soundararajan, R., & Vishwanath, S. (2012) · IEEE Transactions on Information Theory · doi:10.1109/tit.2011.2173632 · Cited by 48
Distortion Outage Minimization and Diversity Order Analysis for Coherent Multiaccess
Wang, C.-H., Leong, A. S., & Dey, S. (2011) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2011.2165950 · Cited by 33
On achievable rates for analog computing real-valued functions over the wireless channel
Goldenbaum, M., Stańczak, S., & Boche, H. (2015) · International Conference on Communications · doi:10.1109/icc.2015.7248955 · Cited by 13
Research works printed but not linked: 15
- 2010, Timing Advance (TA) in LTE
- goodfellow, 2016, Deep Learning
- yang, 2018, Federated learning via over-the-air computation, arXiv 1812 11750
- 10.1109/TWC.2013.022113.120506 · doi:10.1109/twc.2013.022113.120506
- srivastava, 2014, Dropout: A simple way to prevent neural networks from overfitting, J Mach Learn Res, 15, 1929
- arunabha, 2010, Fundamentals of LTE
- kamp, 2018, Efficient decentralized deep learning by dynamic model averaging, arXiv 1807 03210
- chen, 2018, LAG: Lazily aggregated gradient for communication-efficient distributed learning, Proc Conf Neural Inf Process Syst (NIPS), 5055
- lin, 2018, Deep gradient compression: Reducing the communication bandwidth for distributed training, Proc Int Conf Learn Represent (ICLR), 1
- mcmahan, 2017, Communication-efficient learning of deep networks from decentralized data, Proc Int Conf Artif Intell Statist (AISTATS), 1
- zhu, 2018, Broadband analog aggregation for low-latency federated edge learning (extended version), arXiv 1812 11494
- chen, 2017, Revisiting distributed synchronous SGD, arXiv 1604 00981
- zhu, 2018, Towards an intelligent edge: Wireless communication meets machine learning, arXiv 1809 00343
- tandon, 2017, Gradient coding: Avoiding stragglers in distributed learning, Proc Int Conf Mach Learn (ICML), 3368
- poggi, 2017, 3 Key Internet of Things Trends to Keep Your Eye on in 2017
Cited by
Federated Learning via Over-the-Air Computation
Yang, K., Jiang, T., Shi, Y., & Ding, Z. (2020) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2019.2961673 · Cited by 1,084
“This tradeoff between learning and aggregation is also considered in the recent parallel work [30], which quantifies the device population by excluding the devices with weak channel coefficients under deep channel fading and assuming IID located devices.”
BackgroundEdge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
“To tackle the channel fading perturbation, a channel inversion method was proposed in [45], [173], [44] by multiplying the inverse of channel gain for the transmit signal, which may however not satisfy the power constraint at edge devices.”
MethodXu, W., Yang, Z., Ng, D. W. K., Levorato, M., Eldar, Y. C., & Debbah, M. (2023) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2023.3239189 · Cited by 660
Toward an Intelligent Edge: Wireless Communication Meets Machine Learning
Zhu, G., Liu, D., Du, Y., You, C., Zhang, J., & Huang, K. (2020) · IEEE Communications Magazine · doi:10.1109/mcom.001.1900103 · Cited by 606
Self-citationWu, Q., Xu, J., Zeng, Y., Ng, D. W. K., Al-Dhahir, N., Schober, R., & Swindlehurst, A. L. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3088681 · Cited by 562
Metadata
- Authors
- Zhu, G., Wang, Y., & Huang, K.
- Venue
- IEEE Transactions on Wireless Communications
- Published
- 2020-01
- Volume
- 19
- Issue
- 1
- Pages
- 491-506
- ISSN
- 1536-1276 (ISSN-L)
- 1558-2248
- OpenAlex
- W2944099577
- Cited by
- 761
- References
- 24
- FWCI
- 45.58
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Funders
- Hong Kong Research Grants Council (17208319, 17209917, 17259416)
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.