Please wait ...
0% Complete
Home
/
13th International Conference on Computer and Knowledge Engineering
Compressing Deep Neural Networks Using Explainable AI
Authors :
Kimia Soroush
1
Mohsen Raji
2
Behnam Ghavami
3
1- Shiraz university
2- Shiraz university
3- Shahid Bahonar University of Kerman
Keywords :
Deep Neural Networks،Compression،Explainable-AI
Abstract :
Abstract— Deep neural networks (DNNs) have demonstrated remarkable performance in many tasks but it often comes at a high computational cost and memory usage. Compression techniques, such as pruning and quantization, are applied to reduce the memory footprint of DNNs and make it possible to accommodate them on resource-constrained edge devices. Recently, explainable artificial intelligence (XAI) methods have been introduced with the purpose of understanding and explaining AI methods. XAI can be utilized to get to know the inner functioning of DNNs, such as the importance of different neurons and features in the overall performance of DNNs. In this paper, a novel DNN compression approach using XAI is proposed to efficiently reduce the DNN model size with negligible accuracy loss. In the proposed approach, the importance score of DNN parameters (i.e. weights) are computed using a gradient-based XAI technique called Layer-wise Relevance Propagation (LRP). Then, the scores are used to compress the DNN as follows: 1) the parameters with the negative or zero importance scores are pruned and removed from the model, 2) mixed-precision quantization is applied to quantize the weights with higher/lower score with higher/lower number of bits. The experimental results show that, the proposed compression approach reduces the model size by 64% while the accuracy is improved by 42% compared to the state-of-the-art XAI-based compression method.
Papers List
List of archived papers
Optimizing Text-Based Protocol Clustering in Reverse Engineering with Auto-Encoders and Fine-Tuned Parameters
Shiva Mahmoudzadeh - Mohaddese Nemati - Mehdi Teimouri
Vision-Based Obstacle Avoidance in Drone Navigation using Deep Reinforcement Learning
Pooyan Rahmanzadeh Gervi - Ahad Harati - Sayed Kamaledin Ghiasi-Shirazi
Evaluating the Impact of Traveling on COVID-19 Prevalence and Predicting the New Confirmed Cases According to the Travel Rate Using Machine Learning: A Case Study in Iran
Anita Ghandehari - Soheil Shirvani - Hadi Moradi
Semantic Segmentation Using Region Proposals and Weakly-Supervised Learning
Maryam Taghizadeh - Abdolah Chalechale
Brain Age Estimation with Twin Vision Transformer using Hippocampus Information Applicable to Alzheimer Dementia Diagnosis
Zahra Qodrati - Seyedeh Masoumeh Taji - Amirhossein Ghaemi - Habibollah Danyali - Kamran Kazemi - Alireza Ghaemi
FaaScaler: An Automatic Vertical and Horizontal Scaler for Serverless Computing Environments
Zahra Rezaei - Saeid Abrishami - Seid Nima Moeintaghavi
A New Application of Machine Learning Based Methods for Disk Space Variation Fault Diagnosis in Transformer Windings
Reza Behkam - Amir Lotfi - Gevork B. Gharehpetian
Attentional Bi-LSTM for Multivariate Time Series Forecasting on Edge Devices: A Case Study on NanoPi Neo Plus2
Navid Hajizadeh - Saeed Yazdani - Sara Ershadi-Nasab
Virtual Network Embedding based on Univariate Distribution Estimation
Arezoo Jahani
Automated Person Identification from Hand Images\\using Hierarchical Vision Transformer Network
Zahra Ebrahimian - Seyed Ali Mirsharji - Ramin Toosi - Mohammad Ali Akhaee
more
Samin Hamayesh - Version 46.0.2