GHN-Q: Parameter Prediction for Unseen Quantized Convolutional Architectures via Graph Hypernetworks

• URL: http://arxiv.org/abs/2208.12489v2
• Date: Fri, 18 Aug 2023 05:26:31 GMT
• Title: GHN-Q: Parameter Prediction for Unseen Quantized Convolutional Architectures via Graph Hypernetworks
• Authors: Stone Yun, Alexander Wong
• Abstract summary: We conduct the first-ever study exploring the use of graph hypernetworks for predicting parameters of unseen quantized CNN architectures. We focus on a reduced CNN search space and find that GHN-Q can in fact predict quantization-robust parameters for various 8-bit quantized CNNs.
• Score: 80.29667394618625
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Deep convolutional neural network (CNN) training via iterative optimization has had incredible success in finding optimal parameters. However, modern CNN architectures often contain millions of parameters. Thus, any given model for a single architecture resides in a massive parameter space. Models with similar loss could have drastically different characteristics such as adversarial robustness, generalizability, and quantization robustness. For deep learning on the edge, quantization robustness is often crucial. Finding a model that is quantization-robust can sometimes require significant efforts. Recent works using Graph Hypernetworks (GHN) have shown remarkable performance predicting high-performant parameters of varying CNN architectures. Inspired by these successes, we wonder if the graph representations of GHN-2 can be leveraged to predict quantization-robust parameters as well, which we call GHN-Q. We conduct the first-ever study exploring the use of graph hypernetworks for predicting parameters of unseen quantized CNN architectures. We focus on a reduced CNN search space and find that GHN-Q can in fact predict quantization-robust parameters for various 8-bit quantized CNNs. Decent quantized accuracies are observed even with 4-bit quantization despite GHN-Q not being trained on it. Quantized finetuning of GHN-Q at lower bitwidths may bring further improvements and is currently being explored.

Related papers

• Two Heads are Better Than One: Neural Networks Quantization with 2D Hilbert Curve-based Output Representation [3.4606942690643336]
  We introduce a novel approach for DNN quantization that uses a redundant representation of DNN's output. We demonstrate that this mapping can reduce quantization error. Our approach can be applied to other tasks, including segmentation, object detection, and key-points prediction.
  arXiv  Detail & Related papers  (2024-05-22T21:59:46Z)
• GHN-QAT: Training Graph Hypernetworks to Predict Quantization-Robust Parameters of Unseen Limited Precision Neural Networks [80.29667394618625]
  Graph Hypernetworks (GHN) can predict the parameters of varying unseen CNN architectures with surprisingly good accuracy. Preliminary research has explored the use of GHNs to predict quantization-robust parameters for 8-bit and 4-bit quantized CNNs. We show that quantization-aware training can significantly improve quantized accuracy for GHN predicted parameters of 4-bit quantized CNNs.
  arXiv  Detail & Related papers  (2023-09-24T23:01:00Z)
• A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking [124.21408098724551]
  Large-scale graph training is a notoriously challenging problem for graph neural networks (GNNs) We present a new ensembling training manner, named EnGCN, to address the existing issues. Our proposed method has achieved new state-of-the-art (SOTA) performance on large-scale datasets.
  arXiv  Detail & Related papers  (2022-10-14T03:43:05Z)
• Toward Trainability of Quantum Neural Networks [87.04438831673063]
  Quantum Neural Networks (QNNs) have been proposed as generalizations of classical neural networks to achieve the quantum speed-up. Serious bottlenecks exist for training QNNs due to the vanishing with gradient rate exponential to the input qubit number. We show that QNNs with tree tensor and step controlled structures for the application of binary classification. Simulations show faster convergent rates and better accuracy compared to QNNs with random structures.
  arXiv  Detail & Related papers  (2020-11-12T08:32:04Z)
• Absence of Barren Plateaus in Quantum Convolutional Neural Networks [0.0]
  Quantum Convolutional Neural Networks (QCNNs) have been proposed. We rigorously analyze the gradient scaling for the parameters in the QCNN architecture.
  arXiv  Detail & Related papers  (2020-11-05T16:46:13Z)
• Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search [112.05977301976613]
  We propose to combine Network Architecture Search methods with quantization to enjoy the merits of the two sides. We first propose the joint training of architecture and quantization with a shared step size to acquire a large number of quantized models. Then a bit-inheritance scheme is introduced to transfer the quantized models to the lower bit, which further reduces the time cost and improves the quantization accuracy.
  arXiv  Detail & Related papers  (2020-10-09T03:52:16Z)
• Learned Low Precision Graph Neural Networks [10.269500440688306]
  We show how to systematically quantise Deep Graph Neural Networks (GNNs) with minimal or no loss in performance using Network Architecture Search (NAS) The proposed novel NAS mechanism, named Low Precision Graph NAS (LPGNAS), constrains both architecture and quantisation choices to be differentiable. On eight different datasets, solving the task of classifying unseen nodes in a graph, LPGNAS generates quantised models with significant reductions in both model and buffer sizes.
  arXiv  Detail & Related papers  (2020-09-19T13:51:09Z)
• Degree-Quant: Quantization-Aware Training for Graph Neural Networks [10.330195866109312]
  Graph neural networks (GNNs) have demonstrated strong performance on a wide variety of tasks. Despite their promise, there exists little research exploring methods to make them more efficient at inference time. We propose an architecturally-agnostic method, Degree-Quant, to improve performance over existing quantization-aware training baselines.
  arXiv  Detail & Related papers  (2020-08-11T20:53:50Z)
• Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
  Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques. We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
  arXiv  Detail & Related papers  (2020-02-03T04:11:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.