mlsanityData to 7 Oct 2026

Knowledge Grafting: A Mechanism for Optimizing AI Model Deployment in Resource-Constrained Environments

arXiv 2507.19261 ↗First posted 25 Jul 2025cs.AI cs.LG cs.PFcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 37 references that are in the map. First posted on arXiv 25 Jul 2025.

Builds on

25 of 37 references.

References · 25

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  6. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  8. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  9. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  10. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  11. 2014How transferable are features in deep neural networks?cited by 1,216
  12. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
13 more
  1. 2018Do Better ImageNet Models Transfer Better?cited by 560
  2. 2019Quantifying the Carbon Emissions of Machine Learningcited by 516
  3. 2023Augmented Language Models: a Surveycited by 398
  4. 2018Model compression via distillation and quantizationcited by 287
  5. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  6. 2016Dynamic Network Surgery for Efficient DNNscited by 233
  7. 2016Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruningcited by 133
  8. 2016An Analysis of Deep Neural Network Models for Practical Applicationscited by 114
  9. 2018DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learningcited by 69
  10. 2024CrossFuse: A Novel Cross Attention Mechanism based Infrared and Visible Image Fusion Approachcited by 38
  11. 2024Routing Experts: Learning to Route Dynamic Experts in Multi-modal Large Language Modelscited by 13
  12. 2024Measuring the Energy Consumption and Efficiency of Deep Neural Networks: An Empirical Analysis and Design Recommendationscited by 11
  13. 2024Scalify: scale propagation for efficient low-precision LLM trainingcited by 4

Built on by

Not cited yet.