GHN-QAT: Training Graph Hypernetworks to Predict Quantization-Robust
Parameters of Unseen Limited Precision Neural Networks

GHN-QAT: Training Graph Hypernetworks to Predict Quantization-Robust Parameters of Unseen Limited Precision Neural Networks

24 September 2023

Alexander Wong

Papers citing "GHN-QAT: Training Graph Hypernetworks to Predict Quantization-Robust Parameters of Unseen Limited Precision Neural Networks"

6 / 6 papers shown

Title
GHN-Q: Parameter Prediction for Unseen Quantized Convolutional Architectures via Graph Hypernetworks S. Yun Alexander Wong GNN MQ 23 1 0 26 Aug 2022
Parameter Prediction for Unseen Deep Architectures Boris Knyazev M. Drozdzal Graham W. Taylor Adriana Romero Soriano OOD 81 83 0 25 Oct 2021
Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamics S. Yun Alexander Wong MQ 60 26 0 24 Apr 2021
Where Should We Begin? A Low-Level Exploration of Weight Initialization Impact on Quantized Behaviour of Deep Neural Networks S. Yun A. Wong MQ 36 4 0 30 Nov 2020
Data-Free Quantization Through Weight Equalization and Bias Correction Markus Nagel M. V. Baalen Tijmen Blankevoort Max Welling MQ 70 512 0 11 Jun 2019
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference Benoit Jacob S. Kligys Bo Chen Menglong Zhu Matthew Tang Andrew G. Howard Hartwig Adam Dmitry Kalenichenko MQ 150 3,123 0 15 Dec 2017