FTT-NAS: Discovering Fault-Tolerant Neural Architecture
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
With the fast evolvement of deep-learning specific embedded computing systems, applications powered by deep learning are moving from the cloud to the edge. When deploying NNs onto the edge devices under complex environments, there are various types of possible faults: soft errors caused by atmospheric neutrons and radioactive impurities, voltage instability, aging, temperature variations, and malicious attackers. Thus the safety risk of deploying neural networks at edge computing devices in safety-critic applications is now drawing much attention. In this paper, we implement the random bit-flip, Gaussian, and Salt-and-Pepper fault models and establish a multi-objective fault-tolerant neural architecture search framework. On top of the NAS framework, we propose Fault-Tolerant Neural Architecture Search (FT-NAS) to automatically discover convolutional neural network (CNN) architectures that are reliable to various faults in nowadays edge devices. Then we incorporate fault-tolerant training (FTT) in the search process to achieve better results, which we called FTT-NAS. Experiments show that the discovered architecture FT-NAS-Net and FTT-NAS-Net outperform other hand-designed baseline architectures (58.1%/86.6% VS. 10.0%/52.2%), with comparable FLOPs and less parameters. What is more, the architectures trained under a single fault model can also defend against other faults. By inspecting the discovered architecture, we find that there are redundant connections learned to protect the sensitive paths. This insight can guide future fault-tolerant neural architecture design, and we verify it by a modification on ResNet-20-ResNet-M.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
MnasNet: Platform-Aware Neural Architecture Search for Mobile
Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., & Le, Q. V. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00293 · Cited by 3,416 · cited 1×
“[25, 29] used multiple objectives to learn architectures with better accuracy and lower latency simultaneously.”
DARTS: Differentiable architecture search
Liu, H., Simonyan, K., & Yang, Y. (2018) · arXiv · doi:10.48550/arxiv.1806.09055 · Cited by 3,248
Efficient multi-objective neural architecture search via Lamarckian evolution
Elsken, T., Metzen, J. H., & Hutter, F. (2018) · arXiv · doi:10.48550/arxiv.1804.09081 · Cited by 311
A Reliability Analysis of a Deep Neural Network
Bosio, A., Bernardi, P., Ruospo, A., & Sanchez, E. (2019) · 2019 IEEE Latin American Test Symposium (LATS) · doi:10.1109/latw.2019.8704548 · Cited by 114 · cited 2×
“[10, 11] analyzed the robustness of neural networks from the view of algorithms with Stuck-at-Fault (SaF) model.”
The Robustness of Modern Deep Learning Architectures against Single Event Upset Errors
Arechiga, A. P., & Michaels, A. J. (2018) · 2018 IEEE High Performance extreme Computing Conference (HPEC) · doi:10.1109/hpec.2018.8547532 · Cited by 47
Cited by
Neural Architecture Search for Transformers: A Survey
Chitty-Venkata, K. T., Emani, M., Vishwanath, V., & Somani, A. K. (2022) · IEEE Access · doi:10.1109/access.2022.3212767 · Cited by 118
Neural Architecture Search Survey: A Hardware Perspective
Chitty-Venkata, K. T., & Somani, A. K. (2023) · ACM Computing Surveys · doi:10.1145/3524500 · Cited by 106
“Li et al. proposed FTT-NAS [77] to search for networks that are dependable on various faulty conditions such as random bit-flip, Gaussian, and so on, by combining fault tolerant NAS (FT-NAS) and fault tolerant training (FTT) .”
BackgroundNAS4RRAM: neural network architecture search for inference on RRAM-based accelerators
Yuan, Z., Liu, J., Li, X., Yan, L., Chen, H., Wu, B., Yang, Y., & Sun, G. (2021) · Science China Information Sciences · doi:10.1007/s11432-020-3245-7 · Cited by 30
Winograd convolution: a perspective from fault tolerance
Xue, X., Huang, H., Liu, C., Luo, T., Zhang, L., & Wang, Y. (2022) · Proceedings of the 59th ACM/IEEE Design Automation Conference · doi:10.1145/3489517.3530531 · Cited by 10
Self-citation
Metadata
- Authors
- Li, W., Ning, X., Ge, G., Chen, X., Wang, Y., & Yang, H.
- Venue
- 2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC)
- Publisher
- IEEE
- Published
- 2020-01
- Pages
- 211-216
- OpenAlex
- W3014017759
- Cited by
- 34
- References
- 7
- FWCI
- 2.35
- 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: FTT-NAS: Discovering Fault-Tolerant Neural Architecture. https://app.cochat.ai/papers/10.1109/asp-dac47756.2020.9045324
- The paper
- Li, W., Ning, X., Ge, G., Chen, X., Wang, Y., & Yang, H. (2020). FTT-NAS: Discovering Fault-Tolerant Neural Architecture. 2020 25th Asia and South Pacific Design Automation Conference (ASP-DAC). https://doi.org/10.1109/asp-dac47756.2020.9045324
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.