MTL-Split: Multi-Task Learning for Edge Devices using Split Computing
Not on the map. Why?
Abstract (arXiv)
Split Computing (SC), where a Deep Neural Network (DNN) is intelligently split with a part of it deployed on an edge device and the rest on a remote server is emerging as a promising approach. It allows the power of DNNs to be leveraged for latency-sensitive applications that do not allow the entire DNN to be deployed remotely, while not having sufficient computation bandwidth available locally. In many such embedded systems scenarios, such as those in the automotive domain, computational resource constraints also necessitate Multi-Task Learning (MTL), where the same DNN is used for multiple inference tasks instead of having dedicated DNNs for each task, which would need more computing bandwidth. However, how to partition such a multi-tasking DNN to be deployed within a SC framework has not been sufficiently studied. This paper studies this problem, and MTL-Split, our novel proposed architecture, shows encouraging results on both synthetic and real-world data. The source code is available at https://github.com/intelligolabs/MTL-Split.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 17 of its 30 references that are in the map. First posted on arXiv 8 Jul 2024.
Builds on
17 of 30 references.
References · 17
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
- 2020Knowledge Distillation: A Surveycited by 1,578
- 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
- 2018Multi-Task Learning as Multi-Objective Optimizationcited by 809
- 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
- 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 367
- 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
- 2022Multi-Task Learning as a Bargaining Gamecited by 209
- 2018NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reductioncited by 127
- 2021Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challengescited by 114
- 2018JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Servicescited by 79
5 more
- 2018Deep feature compression for collaborative object detectioncited by 48
- 2018Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edgecited by 20
- 2021MEDIC: A Multi-Task Learning Dataset for Disaster Image Classificationcited by 20
- 2022Trace norm regularization for multi-task learning with scarce datacited by 10
- 2022I-SPLIT: Deep Network Interpretability for Split Computingcited by 7
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 1.
2 papers.