# FELARE: Fair Scheduling of Machine Learning Tasks on Heterogeneous Edge Systems

arXiv: https://arxiv.org/abs/2206.00065 · HTML: https://mlsanity.com/paper/2206.00065/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 41 references that are in the map.
- First posted on arXiv 31 May 2022.

## Builds on (most cited first, 11 of 11)

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation](https://mlsanity.com/paper/2004.09602/) (2020)
- [Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors](https://mlsanity.com/paper/2006.10159/) (2020)
- [Improving Robustness of Heterogeneous Serverless Computing Systems Via Probabilistic Task Pruning](https://mlsanity.com/paper/1905.04456/) (2019)
- [Exploring the Impact of Virtualization on the Usability of the Deep Learning Applications](https://mlsanity.com/paper/2112.09780/) (2021)
- [Autonomous Task Dropping Mechanism to Achieve Robustness in Heterogeneous Computing Systems](https://mlsanity.com/paper/2005.11050/) (2020)
- [Robust Dynamic Resource Allocation via Probabilistic Task Pruning in Heterogeneous Computing Systems](https://mlsanity.com/paper/1901.09312/) (2019)
- [Recent Advances in Energy Efficient Resource Management Techniques in Cloud Computing Environments](https://mlsanity.com/paper/2107.06005/) (2021)

## Built on by (most cited first, 1 of 1)

- [Edge-MultiAI: Multi-Tenancy of Latency-Sensitive Deep Learning Applications on Edge](https://mlsanity.com/paper/2211.07130/) (2022)

## Abstract (arXiv)

Edge computing enables smart IoT-based systems via concurrent and continuous execution of latency-sensitive machine learning (ML) applications. These edge-based machine learning systems are often battery-powered (i.e., energy-limited). They use heterogeneous resources with diverse computing performance (e.g., CPU, GPU, and/or FPGAs) to fulfill the latency constraints of ML applications. The challenge is to allocate user requests for different ML applications on the Heterogeneous Edge Computing Systems (HEC) with respect to both the energy and latency constraints of these systems. To this end, we study and analyze resource allocation solutions that can increase the on-time task completion rate while considering the energy constraint. Importantly, we investigate edge-friendly (lightweight) multi-objective mapping heuristics that do not become biased toward a particular application type to achieve the objectives; instead, the heuristics consider "fairness" across the concurrent ML applications in their mapping decisions. Performance evaluations demonstrate that the proposed heuristic outperforms widely-used heuristics in heterogeneous systems in terms of the latency and energy objectives, particularly, at low to moderate request arrival rates. We observed 8.9% improvement in on-time task completion rate and 12.6% in energy-saving without imposing any significant overhead on the edge system.