# QoS-Nets: Adaptive Approximate Neural Network Inference

arXiv: https://arxiv.org/abs/2410.07762 · HTML: https://mlsanity.com/paper/2410.07762/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 10 Oct 2024.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Compute Trends Across Three Eras of Machine Learning](https://mlsanity.com/paper/2202.05924/) (2022)
- [Multiplying Matrices Without Multiplying](https://mlsanity.com/paper/2106.10860/) (2021)
- [ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retraining](https://mlsanity.com/paper/1907.07229/) (2019)
- [Combining Gradients and Probabilities for Heterogeneous Approximation of Neural Networks](https://mlsanity.com/paper/2208.07265/) (2022)

## Abstract (arXiv)

In order to vary the arithmetic resource consumption of neural network applications at runtime, this work proposes the flexible reuse of approximate multipliers for neural network layer computations. We introduce a search algorithm that chooses an appropriate subset of approximate multipliers of a user-defined size from a larger search space and enables retraining to maximize task performance. Unlike previous work, our approach can output more than a single, static assignment of approximate multiplier instances to layers. These different operating points allow a system to gradually adapt its Quality of Service (QoS) to changing environmental conditions by increasing or decreasing its accuracy and resource consumption. QoS-Nets achieves this by reassigning the selected approximate multiplier instances to layers at runtime. To combine multiple operating points with the use of retraining, we propose a fine-tuning scheme that shares the majority of parameters between operating points, with only a small amount of additional parameters required per operating point. In our evaluation on MobileNetV2, QoS-Nets is used to select four approximate multiplier instances for three different operating points. These operating points result in power savings for multiplications between 15.3% and 42.8% at a Top-5 accuracy loss between 0.3 and 2.33 percentage points. Through our fine-tuning scheme, all three operating points only increase the model's parameter count by only 2.75%.