Benchmarking Deep Learning Frameworks: Design Considerations, Metrics and Beyond
The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
With increasing number of open-source deep learning (DL) software tools made available, benchmarking DL software frameworks and systems is in high demand. This paper presents design considerations, metrics and challenges towards developing an effective benchmark for DL software frameworks and illustrate our observations through a comparative study of three popular DL frameworks: TensorFlow, Caffe, and Torch. First, we show that these deep learning frameworks are optimized with their default configurations settings. However, the default configuration optimized on one specific dataset may not work effectively for other datasets with respect to runtime performance and learning accuracy. Second, the default configuration optimized on a dataset by one DL framework does not work well for another DL framework on the same dataset. Third, experiments show that different DL frameworks exhibit different levels of robustness against adversarial examples. Through this study, we envision that unlike traditional performance-driven benchmarks, benchmarking deep learning software frameworks should take into account of both runtime and accuracy and their latent interaction with hyper-parameters and data-dependent configurations of DL frameworks.
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
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859
Towards Deep Learning Models Resistant to Adversarial Attacks
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017) · arXiv · doi:10.48550/arxiv.1706.06083 · Cited by 6,602
The Limitations of Deep Learning in Adversarial Settings
Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z. B., & Swami, A. (2016) · 2016 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2016.36 · Cited by 3,993
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
Goyal, P., Dollár, P., Girshick, R., Noordhuis, P., Wesolowski, L., Kyrola, A., Tulloch, A., Jia, Y., & He, K. (2017) · arXiv · doi:10.48550/arxiv.1706.02677 · Cited by 2,294 · cited 1×
“It is worth noting that by carefully setting some hyper parameters, such as batch size, a weight decay rate, and varying the learning rate as the learning progresses over epochs [30]–[32], we expect further improvement on both accuracy and runtime performance of DNNs.”
BackgroundBig data deep learning: Challenges and perspectives
Chen, X.-W., & Lin, X. (2014) · IEEE Access · doi:10.1109/access.2014.2325029 · Cited by 1,255
Detecting Adversarial Samples from Artifacts
Feinman, R., Curtin, R. R., Shintre, S., & Gardner, A. B. (2017) · arXiv · doi:10.48550/arxiv.1703.00410 · Cited by 606
Cited by
Problems and opportunities in training deep learning software systems: an analysis of variance
Pham, H. V., Qian, S., Wang, J., Lutellier, T., Rosenthal, J., Tan, L., Yu, Y., & Nagappan, N. (2020) · Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering · doi:10.1145/3324884.3416545 · Cited by 100
“However, their target is finding the best networks [30, 86, 121], hardware [92, 121], hyper-parameters [72], and framework [48, 60, 72, 93, 95, 121].”
BackgroundAn Empirical Study of Pre-Trained Model Reuse in the Hugging Face Deep Learning Model Registry
Jiang, W., Synovic, N., Hyatt, M., Schorlemmer, T. R., Sethi, R., Lu, Y.-H., Thiruvathukal, G. K., & Davis, J. C. (2023) · 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE) · doi:10.1109/icse48619.2023.00206 · Cited by 76
Exploring the Impact of Virtualization on the Usability of Deep Learning Applications
Samani, D. G., & Salehi, M. A. (2022) · 2022 22nd IEEE International Symposium on Cluster, Cloud and Internet Computing (CCGrid) · doi:10.1109/ccgrid54584.2022.00054 · Cited by 7
Metadata
- Authors
- Liu, L., Wu, Y., Wei, W., Cao, W., Sahin, S., & Zhang, Q.
- Venue
- 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS)
- Publisher
- IEEE
- Published
- 2018-07
- Pages
- 1258-1269
- OpenAlex
- W2883457665
- Cited by
- 54
- References
- 10
- FWCI
- 5.01
- 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: Benchmarking Deep Learning Frameworks: Design Considerations, Metrics and Beyond. https://app.cochat.ai/papers/10.1109/icdcs.2018.00125
- The paper
- Liu, L., Wu, Y., Wei, W., Cao, W., Sahin, S., & Zhang, Q. (2018). Benchmarking Deep Learning Frameworks: Design Considerations, Metrics and Beyond. 2018 IEEE 38th International Conference on Distributed Computing Systems (ICDCS). https://doi.org/10.1109/icdcs.2018.00125
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.