Coded-InvNet for Resilient Prediction Serving Systems
Not on the map. Why?
Abstract (arXiv)
Inspired by a new coded computation algorithm for invertible functions, we propose Coded-InvNet a new approach to design resilient prediction serving systems that can gracefully handle stragglers or node failures. Coded-InvNet leverages recent findings in the deep learning literature such as invertible neural networks, Manifold Mixup, and domain translation algorithms, identifying interesting research directions that span across machine learning and systems. Our experimental results show that Coded-InvNet can outperform existing approaches, especially when the compute resource overhead is as low as 10%. For instance, without knowing which of the ten workers is going to fail, our algorithm can design a backup task so that it can correctly recover the missing prediction result with an accuracy of 85.9%, significantly outperforming the previous SOTA by 32.5%.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 26 of its 44 references that are in the map. First posted on arXiv 11 Jun 2021.
Builds on
26 of 44 references.
References · 26
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2014Conditional Generative Adversarial Netscited by 2,152
- 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
- 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
- 2016Least Squares Generative Adversarial Networkscited by 1,000
- 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 791
14 more
- 2020What is the State of Neural Network Pruning?cited by 578
- 2018Invertible Residual Networkscited by 364
- 2020The Lipschitz Constant of Self-Attentioncited by 171
- 2018i-RevNet: Deep Invertible Networkscited by 137
- 2018Deep Learning in Mobile and Wireless Networking: A Surveycited by 117
- 2015Speeding Up Distributed Machine Learning Using Codescited by 76
- 2018Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacycited by 66
- 2019MintNet: Building Invertible Neural Networks with Masked Convolutionscited by 35
- 2017PixelGAN Autoencoderscited by 14
- 2020Coded Federated Learningcited by 14
- 2018Hardware-Aware Machine Learning: Modeling and Optimizationcited by 11
- 2016A Unified Coding Framework for Distributed Computing with Straggling Serverscited by 8
- 2018Learning a Code: Machine Learning for Approximate Non-Linear Coded Computationcited by 4
- 2019Slack Squeeze Coded Computing for Adaptive Straggler Mitigationcited by 2
Built on by
Citing papers per year: 2021: 1; 2022: 0; 2023: 0; 2024: 1.
2 papers.