Summary of Mo-emt-nas: Multi-objective Continuous Transfer Of Architectural Knowledge Between Tasks From Different Datasets, by Peng Liao et al.
MO-EMT-NAS: Multi-Objective Continuous Transfer of Architectural Knowledge Between Tasks from Different Datasets
by Peng Liao, XiLu Wang, Yaochu Jin, WenLi Du
First submitted to arxiv on: 18 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers address the challenges of deploying neural network models across diverse devices with different resource constraints. They propose a novel framework called Multi-Objective Evolutionary Multi-Tasking (MO-EMT-NAS) that enables the discovery of Pareto optimal architectures for multiple objectives, including model accuracy and computational efficiency. MO-EMT-NAS achieves this by introducing an auxiliary objective to maintain larger models with similar accuracy and parallelizing training and validation using a weight-sharing-based supernet. The framework is evaluated on seven datasets with various task combinations, showing improved performance and reduced runtime compared to state-of-the-art single-objective multi-tasking algorithms. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps make computer models better by letting them learn from different tasks and devices. It’s like teaching a student to do many things at once, but making sure they don’t forget what they already know. The researchers created a new way to find the best combination of skills and abilities for a model, which is useful when we need to use the same model in many different situations. |
Keywords
» Artificial intelligence » Neural network
