The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Machine Learning at Facebook: Understanding Inference at the Edge
Abstract
At Facebook, machine learning provides a wide range of capabilities that drive many aspects of user experience including ranking posts, content understanding, object detection and tracking for augmented and virtual reality, speech and text translations. While machine learning models are currently trained on customized data-center infrastructure, Facebook is working to bring machine learning inference to the edge. By doing so, user experience is improved with reduced latency (inference time) and becomes less dependent on network connectivity. Furthermore, this also enables many more applications of deep learning with important features only made available at the edge. This paper takes a data-driven approach to present the opportunities and design challenges faced by Facebook in order to enable machine learning inference locally on smart phones and other edge platforms.
Overview
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
Verification
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.
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
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Practical Bayesian Optimization of Machine Learning Algorithms
Snoek, J., Larochelle, H., & Adams, R. P. (2012) · arXiv · doi:10.48550/arxiv.1206.2944 · Cited by 6,691
In-Datacenter Performance Analysis of a Tensor Processing Unit
Jouppi, N. P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., Borchers, A., et al. (2017) · Proceedings of the 44th Annual International Symposium on Computer Architecture · doi:10.1145/3079856.3080246 · Cited by 4,537
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., & Kalenichenko, D. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00286 · Cited by 4,114
Neural Architecture Search with Reinforcement Learning
Zoph, B., & Le, Q. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.01578 · Cited by 3,974
Channel Pruning for Accelerating Very Deep Neural Networks
He, Y., Zhang, X., & Sun, J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.155 · Cited by 2,647
Temporal Convolutional Networks for Action Segmentation and Detection
Lea, C., Flynn, M. D., Vidal, R., Reiter, A., & Hager, G. D. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.113 · Cited by 2,238 · cited 1×
“Hand Tracking U-Net [29] 10x 1x Image Model-1 GoogLeNet [30] 100x 1x Image Model-2 ShuffleNet [27] 10x 2x Pose Estimation Mask-RCNN [28] 100x 4x Segmentation TCN [31] 1x 1.”
Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks
Chen, Y.-H., Emer, J., & Sze, V. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001177 · Cited by 1,182
Li, F., Liu, B., Wang, X., Zhang, B., & Yan, J. (2016) · arXiv · doi:10.48550/arxiv.1605.04711 · Cited by 732
Self-citation
Research works printed but not linked: 54
- 10.1109/ISLPED.2017.8009208 · DOI
- 10.1145/2627369.2627641 · doi:10.1145/2627369.2627641
- 10.1109/ISPASS.2018.00015 · doi:10.1109/ispass.2018.00015
- 10.1109/CVPR.2015.7298594 · DOI · Paper page
- 10.1109/TMC.2018.2883619 · doi:10.1109/tmc.2018.2883619
- 10.1109/HPCA.2016.7446053 · DOI
- ju yu, 2018, Designing a temperature model to understand the thermal challenges of portable computing platforms, Proc Intersociety Conf Thermal and Thermomechanical Phenomena Electron Syst
- 10.1109/ISCA.2018.00062 · DOI · Paper page
- 10.1109/ISCA.2018.00068 · DOI
- 10.1109/ISCA.2018.00063 · DOI · Paper page
- 10.1109/ISCA.2018.00069 · DOI · Paper page
- 10.1109/ICCV.2017.322 · DOI · Paper page
- 10.1109/ISCA.2018.00070 · DOI
- zhang, 2018, ShuffleNet: an extremely efficient convolutional neural network for mobile devices, Proc of the Conference on Computer Vision and Pattern Recognition
- 10.1109/ISCA.2018.00071 · DOI
- 10.1109/ISCA.2018.00016 · DOI
- 2018, Facebook Reports First Quarter 2018 Results
- 10.1109/HPCA.2018.00059 · DOI · Paper page
- courbariaux, 2016, Binarynet: Training deep neural networks with weights and activations constrained to +1 or -1, CoRR vol abs/1602 02830
- park, 2018, Value-aware quantization for training and inference of neural networks, CoRR vol abs/1804 07802
- 0, Acceleration package for neural networks on multi-core cpus
- ronneberger, 2015, U-net Convolutional networks for biomedical image segmentation
- dukhan, 0, QNNPACK open source library for optimized mobile deep learning
- 10.1145/3079856.3080254 · DOI · Paper page
- shen, 2017, Maximizing CNN accelerator efficiency through resource partitioning, Proc of the Intl Symp on Computer Architecture, 10.1145/3140659.3080221 · DOI
- aklaghi, 2018, SnaPEA: Predictive early activation for reducing computation in deep convolutional neural networks, Proc of the Intl Symp on Computer Architecture
- 10.1109/ISCA.2018.00060 · DOI
- 10.1109/HPCA.2018.00018 · DOI
- 10.1109/HPCA.2018.00017 · DOI · Paper page
- 10.1109/HPCA.2018.00016 · DOI
- 10.1109/HPCA.2018.00015 · DOI
- de sa, 2017, Understanding and optimizing asynchronous low-precision stochastic gradient descent, Proc of the Intl Symp on Computer Architecture, 10.1145/3140659.3080248 · DOI
- yu, 2017, Scalpel: Customizing DNN pruning to the underlying hardware parallelism, Proc of the Intl Symp on Computer Architecture, 10.1145/3140659.3080215 · DOI
- rotem, 2018, Glow Graph lowering compiler techniques for neural networks
- 0, XLA is a compiler that optimizes Tensor Flow computations
- zhou, 2018, Resource-efficient neural architect, CoRR vol abs/1806 07912
- chen, 2018, TVM An automated end-to-end optimizing compiler for deep learning
- 0, Core ml Integrate machine learning models into your app
- han, 2015, Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding, CoRR vol abs/1510 00149
- lecun, 1990, Optimal brain damage, Advances in Neural Information Processing Systems 2, 598
- 2018, Enabling full body AR with Mask R-CNN2Go
- 0, gemmlowp a small self-contained low-precision GEMM library
- 0, Qualcomm Neural Processing SDK for AI
- 2017, Mark Zuckerberg 2 billion users means Facebook's ‘responsibility is expanding’
- 10.1109/ISPASS.2015.7095808 · DOI
- 0, Cambricon Makers of Huawei's Kirin NPU IP Build A Big AI Chip and PCIe Card
- 10.1145/3079856.3080244 · DOI · Paper page
- 2018, Caffe2 and pytorch join forces to create a research + production platform pytorch 1 0
- 10.1145/3007787.3001178 · DOI · Paper page
- 10.1145/3007787.3001179 · DOI · Paper page
- 10.1145/3007787.3001139 · DOI · Paper page
- 10.1145/3007787.3001138 · DOI · Paper page
- 10.1145/3007787.3001165 · DOI · Paper page
- 10.1145/3007787.3001163 · DOI · Paper page
Cited by
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2918951 · Cited by 2,455
“On the other hand, unlike high-performance discrete GPUs on the cloud data center, there is no dedicated high-bandwidth memory for mobile GPUs on mobile devices [69].”
BackgroundAligning artificial intelligence with climate change mitigation
Kaack, L. H., Donti, P. L., Strubell, E., Kamiya, G., Creutzig, F., & Rolnick, D. (2022) · Nature Climate Change · doi:10.1038/s41558-022-01377-7 · Cited by 570
Sustainable AI: Environmental Implications, Challenges and Opportunities
Wu, C.-J., Raghavendra, R., Gupta, U., Acun, B., Ardalani, N., Maeng, K., Chang, G., Behram, F. A., Huang, J., Bai, C., et al. (2021) · arXiv · doi:10.48550/arxiv.2111.00364 · Cited by 405
“…high wireless communication overheads, sub-optimal training data distribution in individual client devices [114], large degree of system heterogeneity among client edge devices, and highly-fragmented edge device architectures that make system-level optimization significantly more challenging [116].”
BackgroundSelf-citationExplainable AI for 6G Use Cases: Technical Aspects and Research Challenges
Wang, S., Qureshi, M. A., Miralles-Pechuán, L., Huynh-The, T., Gadekallu, T. R., & Liyanage, M. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3386872 · Cited by 170
Bringing ai to edge: from deep learning’s perspective
Liu, D., Kong, H., Luo, X., Liu, W., & Subramaniam, R. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.04.141 · Cited by 171
“…of service (QoS) of applications without rigorously temporal requirement, like voice recognition, face recognition, machine translation, etc [20] and on the other hand may lead to catastrophic consequence for those with rigorously temporal requirement, (i.e., real-time requirement), like…”
BackgroundInfluential
Metadata
- Authors
- Wu, C.-J., Brooks, D., Chen, K., Chen, D., Choudhury, S., Dukhan, M., Hazelwood, K., Isaac, E., Jia, Y., Jia, B., Leyvand, T., Lu, H., Lu, Y., Qiao, L., Reagen, B., Spisak, J., Sun, F., Tulloch, A., Vajda, P., Wang, X., Wang, Y., Wasti, B., Wu, Y., Xian, R., Yoo, S., & Zhang, P.
- Venue
- 2019 IEEE International Symposium on High Performance Computer Architecture (HPCA)
- Publisher
- IEEE
- Published
- 2019-02
- Pages
- 331-344
- ISSN
- 1530-0897 (ISSN-L)
- OpenAlex
- W2931743911
- Cited by
- 439
- References
- 9
- FWCI
- 66.08
- Type
- conference paper
- Language
- en
- Open access
- closed
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: Machine Learning at Facebook: Understanding Inference at the Edge. https://app.cochat.ai/papers/10.1109/hpca.2019.00048
- The paper
- Wu, C.-J., Brooks, D., Chen, K., Chen, D., Choudhury, S., Dukhan, M., Hazelwood, K., Isaac, E., Jia, Y., Jia, B., Leyvand, T., Lu, H., Lu, Y., Qiao, L., Reagen, B., Spisak, J., Sun, F., Tulloch, A., Vajda, P., . . . Zhang, P. (2019). Machine Learning at Facebook: Understanding Inference at the Edge. 2019 IEEE International Symposium on High Performance Computer Architecture (HPCA). https://doi.org/10.1109/hpca.2019.00048
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.
