Knowledge Grafting: A Mechanism for Optimizing AI Model Deployment in Resource-Constrained Environments
This addresses the challenge of AI deployment on edge devices with limited resources, though it appears incremental as it builds on transfer learning and model compression techniques.
The paper tackles the problem of deploying large AI models in resource-constrained environments by introducing knowledge grafting, which reduces model size by 88.54% while improving validation accuracy from 87.47% to 89.97% and achieving 90.45% accuracy on unseen test data.
The increasing adoption of Artificial Intelligence (AI) has led to larger, more complex models with numerous parameters that require substantial computing power -- resources often unavailable in many real-world application scenarios. Our paper addresses this challenge by introducing knowledge grafting, a novel mechanism that optimizes AI models for resource-constrained environments by transferring selected features (the scion) from a large donor model to a smaller rootstock model. The approach achieves an 88.54% reduction in model size (from 64.39 MB to 7.38 MB), while improving generalization capability of the model. Our new rootstock model achieves 89.97% validation accuracy (vs. donor's 87.47%), maintains lower validation loss (0.2976 vs. 0.5068), and performs exceptionally well on unseen test data with 90.45% accuracy. It addresses the typical size vs performance trade-off, and enables deployment of AI frameworks on resource-constrained devices with enhanced performance. We have tested our approach on an agricultural weed detection scenario, however, it can be extended across various edge computing scenarios, potentially accelerating AI adoption in areas with limited hardware/software support -- by mirroring in a similar manner the horticultural grafting enables productive cultivation in challenging agri-based environments.