arXiv subjects

Ping Xue

Publications and source records attributed to Ping Xue.

12 recordsLinked to original sources

arXiv2026

Preserving Continuous Symmetry in Discrete Spaces: Geometric-Aware Quantization for SO(3)-Equivariant GNNs

Equivariant Graph Neural Networks (GNNs) are essential for physically consistent molecular simulations but suffer from high computational costs and memory bottlenecks, especially with high-order representations. While low-bit quantization offers a solution, applying it naively to rotation-sensitive features destroys the SO(3)-equivariant structure, leading to significant errors and violations of conservation laws. To address this issue, in this work, we propose a Geometric-Aware Quantization (GAQ) framework that compresses and accelerates equivariant models while rigorously preserving continuous symmetry in discrete spaces. Our approach introduces three key contributions: (1) a Magnitude-Direction Decoupled Quantization (MDDQ) scheme that separates invariant lengths from equivariant orientations to maintain geometric fidelity; (2) a symmetry-aware training strategy that treats scalar and vector features with distinct quantization schedules; and (3) a robust attention normalization mechanism to stabilize gradients in low-bit regimes. Experiments on the rMD17 benchmark demonstrate that our W4A8 models match the accuracy of FP32 baselines (9.31 meV vs. 23.20 meV) while reducing Local Equivariance Error (LEE) by over 30x compared to naive quantization. On consumer hardware, GAQ achieves 2.39x inference speedup and 4x memory reduction, enabling stable, energy-conserving molecular dynamics simulations for nanosecond timescales.

cs.LG↗

arXiv2026

Quantized SO(3)-Equivariant Graph Neural Networks for Efficient Molecular Property Prediction

Deploying 3D graph neural networks (GNNs) that are equivariant to 3D rotations (the group SO(3)) on edge devices is challenging due to their high computational cost. This paper addresses the problem by compressing and accelerating an SO(3)-equivariant GNN using low-bit quantization techniques. Specifically, we introduce three innovations for quantized equivariant transformers: (1) a magnitude-direction decoupled quantization scheme that separately quantizes the norm and orientation of equivariant (vector) features, (2) a branch-separated quantization-aware training strategy that treats invariant and equivariant feature channels differently in an attention-based $SO(3)$-GNN, and (3) a robustness-enhancing attention normalization mechanism that stabilizes low-precision attention computations. Experiments on the QM9 and rMD17 molecular benchmarks demonstrate that our 8-bit models achieve accuracy on energy and force predictions comparable to full-precision baselines with markedly improved efficiency. We also conduct ablation studies to quantify the contribution of each component to maintain accuracy and equivariance under quantization, using the Local error of equivariance (LEE) metric. The proposed techniques enable the deployment of symmetry-aware GNNs in practical chemistry applications with 2.37--2.73x faster inference and 4x smaller model size, without sacrificing accuracy or physical symmetry.

cs.LG↗

arXiv2024

First-in-human spinal cord tumor imaging with fast adaptive focus tracking robotic-OCT

Current surgical procedures for spinal cord tumors lack in vivo high-resolution, high-speed multifunctional imaging systems, posing challenges for precise tumor resection and intraoperative decision-making. This study introduces the Fast Adaptive Focus Tracking Robotic Optical Coherence Tomography (FACT-ROCT) system,designed to overcome these obstacles by providing real-time, artifact-free multifunctional imaging of spinal cord tumors during surgery. By integrating cross-scanning, adaptive focus tracking and robotics, the system addresses motion artifacts and resolution degradation from tissue movement, achieving wide-area, high-resolution imaging. We conducted intraoperative imaging on 21 patients, including 13 with spinal gliomas and 8 with other tumors. This study marks the first demonstration of OCT in situ imaging of human spinal cord tumors, providing micrometer-scale in vivo structural images and demonstrating FACT-ROCT's potential to differentiate various tumor types in real-time. Analysis of the attenuation coefficients of spinal gliomas revealed increased heterogeneity with higher malignancy grades. So, we proposed the standard deviation of the attenuation coefficient as a physical marker, achieving over 90% accuracy in distinguishing high- from low-grade gliomas intraoperatively at a threshold. FACT-ROCT even enabled extensive in vivo microvascular imaging of spinal cord tumors, covering 70 mm * 13 mm * 10 mm within 2 minutes. Quantitative vascular tortuosity comparisons confirmed greater tortuosity in higher-grade tumors. The ability to perform extensive vascular imaging and real-time tumor grading during surgery provides critical information for surgical strategy, such as minimizing intraoperative bleeding and optimizing tumor resection while preserving functional tissue.

physics.optics↗

arXiv2024

Optical biomarker of metabolism for breast tumor diagnosis: Insights from subcellular dynamics

Label-free metabolic dynamics contrast is highly appealing but difficult to achieve in biomedical imaging. Interference offers a highly sensitive mechanism for capturing the metabolic dynamics of the subcellular scatterers. However, traditional interference detection methods fail to isolate pure metabolic dynamics, as the dynamic signals are coupled with scatterer reflectivity and other uncontrollable imaging factors. Here, we demonstrate active phase modulation-assisted dynamic full-field optical coherence tomography (APMD-FFOCT) that decouples and quantifies the metabolic dynamics by adding a reference movement for all interferential scatterers. This novel technique enables imaging and dynamic analysis of subcellular structures along with their changes during the apoptotic process in tumor tissues. Furthermore, the nucleus-to-cytoplasm dynamic intensity ratio could serve as an optical biomarker for breast tumor grading, enhancing intraoperative diagnosis.

physics.med-ph↗

arXiv2024

Fast and label-free 3D virtual H&E histology via active modulation-assisted dynamic full-field OCT

Pathological features are the gold standard for tumor diagnosis, guiding treatment and prognosis. However, standard histopathological process is labor-intensive and time-consuming, while frozen sections have lower accuracy. Dynamic full-field optical coherence tomography (D-FFOCT) offers rapid histologic information by measuring the subcellular dynamics of fresh, unprocessed tissues. However, D-FFOCT images suffer from abrupt shifts in hue and brightness, which is confusing for pathologists and diminish their interpretability and reliability. Here, we present active phase modulation-assisted D-FFOCT (APMD-FFOCT) to improve the imaging stability and enhance the contrast of static tissues. This enables us to further employ an unsupervised deep learning to convert APMD-FFOCT images into virtual hematoxylin and eosin (H&E) stained images for the first time. Three-dimensional (3D) virtual H&E-stained images have been obtained at a scanning rate of 1 frame per second, as demonstrated in cancer diagnosis for human central nervous system and breast. The results prove that this new method will play a unique and important role in intraoperative histology.

physics.med-ph↗

arXiv2023

Generation of cold polyatomic cations by cascade reactive two-body ion-atom collisions

Polyatomic cations $^{87}$Rb$_M^+$ ($M$ = 2, 3,$\ldots$) have been produced by cascade two-body ion-atom reactive collisions in the two-step CW-laser photoionization of laser-cooled $^{87}$Rb atoms and accumulated in the ion trap. Using resonant-excitation mass spectrometry and resonant excitation-assisted time-of-flight mass spectrometry, we directly observed and distinguished the charged reaction products. We experimentally verified the cascade generation and cascade dissociation of $^{87}$Rb$_M^+$. The populations of $^{87}$Rb$_M^+$ are quantitatively investigated by solving the rate equations. The $^{87}$Rb$^+$-$^{87}$Rb reaction rate coefficient was derived as 9.10$\times10^{-11}$ cm$^3$/s accordingly. The methods developed here for assembling and detecting homonuclear polyatomic cations can be applied to any experiment in ion-atom hybrid traps. The present study lays the foundation for exploring atomically precise metal clusters and physics from few- to many-body perspective.

physics.atom-ph↗

arXiv2023

Evolution of the number and temperature of the remaining cold atoms in CW-laser photoionization of laser-cooled $^{87}$Rb atoms

Based on the Rb$^+$-Rb hybrid trap, we investigate the effect of ion-atom elastic collisions on the number and temperature of the remaining atoms. We measured the remaining atomic number and temperature as a function of the wavelength and intensity of the ionization laser, and whether the ion trap was turned on. Fittings with a single exponential decay function plus an offset to the number and radius of the remaining atoms are found to be in good agreement. We found a difference in the exponential factor of different wavelengths of ionization laser with the ion trap on or off. We suppose that the presence of electrons affects ion-atom collisions through disorder-induced heating. Our research contributes to a better understanding of how ultracold neutral plasma evolves, particularly the subsequent kinetics of atomic processes, which also serves as a useful reference for high-energy-density plasma.

physics.atom-ph↗

arXiv2022

IR2Net: Information Restriction and Information Recovery for Accurate Binary Neural Networks

Weight and activation binarization can efficiently compress deep neural networks and accelerate model inference, but cause severe accuracy degradation. Existing optimization methods for binary neural networks (BNNs) focus on fitting full-precision networks to reduce quantization errors, and suffer from the trade-off between accuracy and computational complexity. In contrast, considering the limited learning ability and information loss caused by the limited representational capability of BNNs, we propose IR$^2$Net to stimulate the potential of BNNs and improve the network accuracy by restricting the input information and recovering the feature information, including: 1) information restriction: for a BNN, by evaluating the learning ability on the input information, discarding some of the information it cannot focus on, and limiting the amount of input information to match its learning ability; 2) information recovery: due to the information loss in forward propagation, the output feature information of the network is not enough to support accurate classification. By selecting some shallow feature maps with richer information, and fusing them with the final feature maps to recover the feature information. In addition, the computational cost is reduced by streamlining the information recovery method to strike a better trade-off between accuracy and efficiency. Experimental results demonstrate that our approach still achieves comparable accuracy even with $ \sim $10x floating-point operations (FLOPs) reduction for ResNet-18. The models and code are available at https://github.com/pingxue-hfut/IR2Net.

cs.CV↗

arXiv2021

AIP: Adversarial Iterative Pruning Based on Knowledge Transfer for Convolutional Neural Networks

With the increase of structure complexity, convolutional neural networks (CNNs) take a fair amount of computation cost. Meanwhile, existing research reveals the salient parameter redundancy in CNNs. The current pruning methods can compress CNNs with little performance drop, but when the pruning ratio increases, the accuracy loss is more serious. Moreover, some iterative pruning methods are difficult to accurately identify and delete unimportant parameters due to the accuracy drop during pruning. We propose a novel adversarial iterative pruning method (AIP) for CNNs based on knowledge transfer. The original network is regarded as the teacher while the compressed network is the student. We apply attention maps and output features to transfer information from the teacher to the student. Then, a shallow fully-connected network is designed as the discriminator to allow the output of two networks to play an adversarial game, thereby it can quickly recover the pruned accuracy among pruning intervals. Finally, an iterative pruning scheme based on the importance of channels is proposed. We conduct extensive experiments on the image classification tasks CIFAR-10, CIFAR-100, and ILSVRC-2012 to verify our pruning method can achieve efficient compression for CNNs even without accuracy loss. On the ILSVRC-2012, when removing 36.78% parameters and 45.55% floating-point operations (FLOPs) of ResNet-18, the Top-1 accuracy drop are only 0.66%. Our method is superior to some state-of-the-art pruning schemes in terms of compressing rate and accuracy. Moreover, we further demonstrate that AIP has good generalization on the object detection task PASCAL VOC.

cs.CV↗

arXiv2021

Self-Distribution Binary Neural Networks

In this work, we study the binary neural networks (BNNs) of which both the weights and activations are binary (i.e., 1-bit representation). Feature representation is critical for deep neural networks, while in BNNs, the features only differ in signs. Prior work introduces scaling factors into binary weights and activations to reduce the quantization error and effectively improves the classification accuracy of BNNs. However, the scaling factors not only increase the computational complexity of networks, but also make no sense to the signs of binary features. To this end, Self-Distribution Binary Neural Network (SD-BNN) is proposed. Firstly, we utilize Activation Self Distribution (ASD) to adaptively adjust the sign distribution of activations, thereby improve the sign differences of the outputs of the convolution. Secondly, we adjust the sign distribution of weights through Weight Self Distribution (WSD) and then fine-tune the sign distribution of the outputs of the convolution. Extensive experiments on CIFAR-10 and ImageNet datasets with various network structures show that the proposed SD-BNN consistently outperforms the state-of-the-art (SOTA) BNNs (e.g., achieves 92.5% on CIFAR-10 and 66.5% on ImageNet with ResNet-18) with less computation cost. Code is available at https://github.com/ pingxue-hfut/SD-BNN.

cs.CV↗

arXiv2021

ACP: Automatic Channel Pruning via Clustering and Swarm Intelligence Optimization for CNN

As the convolutional neural network (CNN) gets deeper and wider in recent years, the requirements for the amount of data and hardware resources have gradually increased. Meanwhile, CNN also reveals salient redundancy in several tasks. The existing magnitude-based pruning methods are efficient, but the performance of the compressed network is unpredictable. While the accuracy loss after pruning based on the structure sensitivity is relatively slight, the process is time-consuming and the algorithm complexity is notable. In this article, we propose a novel automatic channel pruning method (ACP). Specifically, we firstly perform layer-wise channel clustering via the similarity of the feature maps to perform preliminary pruning on the network. Then a population initialization method is introduced to transform the pruned structure into a candidate population. Finally, we conduct searching and optimizing iteratively based on the particle swarm optimization (PSO) to find the optimal compressed structure. The compact network is then retrained to mitigate the accuracy loss from pruning. Our method is evaluated against several state-of-the-art CNNs on three different classification datasets CIFAR-10/100 and ILSVRC-2012. On the ILSVRC-2012, when removing 64.36% parameters and 63.34% floating-point operations (FLOPs) of ResNet-50, the Top-1 and Top-5 accuracy drop are less than 0.9%. Moreover, we demonstrate that without harming overall performance it is possible to compress SSD by more than 50% on the target detection dataset PASCAL VOC. It further verifies that the proposed method can also be applied to other CNNs and application scenarios.

cs.CV↗

arXiv2020

UCP: Uniform Channel Pruning for Deep Convolutional Neural Networks Compression and Acceleration

To apply deep CNNs to mobile terminals and portable devices, many scholars have recently worked on the compressing and accelerating deep convolutional neural networks. Based on this, we propose a novel uniform channel pruning (UCP) method to prune deep CNN, and the modified squeeze-and-excitation blocks (MSEB) is used to measure the importance of the channels in the convolutional layers. The unimportant channels, including convolutional kernels related to them, are pruned directly, which greatly reduces the storage cost and the number of calculations. There are two types of residual blocks in ResNet. For ResNet with bottlenecks, we use the pruning method with traditional CNN to trim the 3x3 convolutional layer in the middle of the blocks. For ResNet with basic residual blocks, we propose an approach to consistently prune all residual blocks in the same stage to ensure that the compact network structure is dimensionally correct. Considering that the network loses considerable information after pruning and that the larger the pruning amplitude is, the more information that will be lost, we do not choose fine-tuning but retrain from scratch to restore the accuracy of the network after pruning. Finally, we verified our method on CIFAR-10, CIFAR-100 and ILSVRC-2012 for image classification. The results indicate that the performance of the compact network after retraining from scratch, when the pruning rate is small, is better than the original network. Even when the pruning amplitude is large, the accuracy can be maintained or decreased slightly. On the CIFAR-100, when reducing the parameters and FLOPs up to 82% and 62% respectively, the accuracy of VGG-19 even improved by 0.54% after retraining.

cs.CV↗