# Numerical Stability of DeepGOPlus Inference

arXiv: https://arxiv.org/abs/2212.06361 · HTML: https://mlsanity.com/paper/2212.06361/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 65 references that are in the map.
- First posted on arXiv 13 Dec 2022.

## Builds on (most cited first, 15 of 15)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [Deep Learning with Limited Numerical Precision](https://mlsanity.com/paper/1502.02551/) (2015)
- [Stable Architectures for Deep Neural Networks](https://mlsanity.com/paper/1705.03341/) (2017)
- [A Study of BFLOAT16 for Deep Learning Training](https://mlsanity.com/paper/1905.12322/) (2019)
- [Training Deep Neural Networks with 8-bit Floating Point Numbers](https://mlsanity.com/paper/1812.08011/) (2018)
- [Improving the Robustness of Deep Neural Networks via Stability Training](https://mlsanity.com/paper/1604.04326/) (2016)
- [Fast Algorithms for Convolutional Neural Networks](https://mlsanity.com/paper/1509.09308/) (2015)
- [Mixed Precision Training With 8-bit Floating Point](https://mlsanity.com/paper/1905.12334/) (2019)
- [Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep Networks](https://mlsanity.com/paper/1901.06588/) (2019)
- [DeepStability: A Study of Unstable Numerical Methods and Their Solutions in Deep Learning](https://mlsanity.com/paper/2202.03493/) (2022)
- [Achieving Generalizable Robustness of Deep Neural Networks by Stability Training](https://mlsanity.com/paper/1906.00735/) (2019)
- [Comparing Perturbation Models for Evaluating Stability of Neuroimaging Pipelines](https://mlsanity.com/paper/1908.10922/) (2019)
- [PyTracer: Automatically profiling numerical instabilities in Python](https://mlsanity.com/paper/2112.11508/) (2021)

## Abstract (arXiv)

Convolutional neural networks (CNNs) are currently among the most widely-used deep neural network (DNN) architectures available and achieve state-of-the-art performance for many problems. Originally applied to computer vision tasks, CNNs work well with any data with a spatial relationship, besides images, and have been applied to different fields. However, recent works have highlighted numerical stability challenges in DNNs, which also relates to their known sensitivity to noise injection. These challenges can jeopardise their performance and reliability. This paper investigates DeepGOPlus, a CNN that predicts protein function. DeepGOPlus has achieved state-of-the-art performance and can successfully take advantage and annotate the abounding protein sequences emerging in proteomics. We determine the numerical stability of the model's inference stage by quantifying the numerical uncertainty resulting from perturbations of the underlying floating-point data. In addition, we explore the opportunity to use reduced-precision floating point formats for DeepGOPlus inference, to reduce memory consumption and latency. This is achieved by instrumenting DeepGOPlus' execution using Monte Carlo Arithmetic, a technique that experimentally quantifies floating point operation errors and VPREC, a tool that emulates results with customizable floating point precision formats. Focus is placed on the inference stage as it is the primary deliverable of the DeepGOPlus model, widely applicable across different environments. All in all, our results show that although the DeepGOPlus CNN is very stable numerically, it can only be selectively implemented with lower-precision floating-point formats. We conclude that predictions obtained from the pre-trained DeepGOPlus model are very reliable numerically, and use existing floating-point formats efficiently.