# Coded-InvNet for Resilient Prediction Serving Systems

arXiv: https://arxiv.org/abs/2106.06445 · HTML: https://mlsanity.com/paper/2106.06445/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 11 Jun 2021.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [Invertible Residual Networks](https://mlsanity.com/paper/1811.00995/) (2018)
- [The Lipschitz Constant of Self-Attention](https://mlsanity.com/paper/2006.04710/) (2020)
- [i-RevNet: Deep Invertible Networks](https://mlsanity.com/paper/1802.07088/) (2018)
- [Deep Learning in Mobile and Wireless Networking: A Survey](https://mlsanity.com/paper/1803.04311/) (2018)
- [Speeding Up Distributed Machine Learning Using Codes](https://mlsanity.com/paper/1512.02673/) (2015)
- [Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacy](https://mlsanity.com/paper/1806.00939/) (2018)
- [MintNet: Building Invertible Neural Networks with Masked Convolutions](https://mlsanity.com/paper/1907.07945/) (2019)
- [PixelGAN Autoencoders](https://mlsanity.com/paper/1706.00531/) (2017)
- [Coded Federated Learning](https://mlsanity.com/paper/2002.09574/) (2020)
- [Hardware-Aware Machine Learning: Modeling and Optimization](https://mlsanity.com/paper/1809.05476/) (2018)
- [A Unified Coding Framework for Distributed Computing with Straggling Servers](https://mlsanity.com/paper/1609.01690/) (2016)
- [Learning a Code: Machine Learning for Approximate Non-Linear Coded Computation](https://mlsanity.com/paper/1806.01259/) (2018)
- [Slack Squeeze Coded Computing for Adaptive Straggler Mitigation](https://mlsanity.com/paper/1904.07098/) (2019)

## Built on by (most cited first, 2 of 2)

- [ApproxIFER: A Model-Agnostic Approach to Resilient and Robust Prediction Serving Systems](https://mlsanity.com/paper/2109.09868/) (2021)
- [NeRCC: Nested-Regression Coded Computing for Resilient Distributed Prediction Serving Systems](https://mlsanity.com/paper/2402.04377/) (2024)

## 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%.