# MIME: Adapting a Single Neural Network for Multi-task Inference with Memory-efficient Dynamic Pruning

arXiv: https://arxiv.org/abs/2204.05274 · HTML: https://mlsanity.com/paper/2204.05274/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 33 references that are in the map.
- First posted on arXiv 11 Apr 2022.

## Builds on (most cited first, 14 of 14)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [A Survey on Deep Transfer Learning](https://mlsanity.com/paper/1808.01974/) (2018)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [Proving the Lottery Ticket Hypothesis: Pruning is All You Need](https://mlsanity.com/paper/2002.00585/) (2020)
- [Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning](https://mlsanity.com/paper/1611.05128/) (2016)
- [A Primer on Neural Network Models for Natural Language Processing](https://mlsanity.com/paper/1510.00726/) (2015)
- [Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers](https://mlsanity.com/paper/2005.06870/) (2020)
- [Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking](https://mlsanity.com/paper/1806.04321/) (2018)
- [FixyNN: Efficient Hardware for Mobile Computer Vision via Transfer Learning](https://mlsanity.com/paper/1902.11128/) (2019)

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

- [Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN](https://mlsanity.com/paper/2305.19868/) (2023)
- [FemtoDet: An Object Detection Baseline for Energy Versus Performance Tradeoffs](https://mlsanity.com/paper/2301.06719/) (2023)

## Abstract (arXiv)

Recent years have seen a paradigm shift towards multi-task learning. This calls for memory and energy-efficient solutions for inference in a multi-task scenario. We propose an algorithm-hardware co-design approach called MIME. MIME reuses the weight parameters of a trained parent task and learns task-specific threshold parameters for inference on multiple child tasks. We find that MIME results in highly memory-efficient DRAM storage of neural-network parameters for multiple tasks compared to conventional multi-task inference. In addition, MIME results in input-dependent dynamic neuronal pruning, thereby enabling energy-efficient inference with higher throughput on a systolic-array hardware. Our experiments with benchmark datasets (child tasks)- CIFAR10, CIFAR100, and Fashion-MNIST, show that MIME achieves ~3.48x memory-efficiency and ~2.4-3.1x energy-savings compared to conventional multi-task inference in Pipelined task mode.