arXiv subjects

Zhenghao Li

Publications and source records attributed to Zhenghao Li.

29 records · Page 2Linked to original sources

arXiv2025

Topological network analysis using a programmable photonic quantum processor

Understanding topological features in networks is crucial for unravelling complex phenomena across fields such as neuroscience, condensed matter, and high-energy physics. However, identifying higher-order topological structures -- such as $k$-cliques, fundamental building blocks of complex networks -- remains a significant challenge. Here we develop a universal programmable photonic quantum processor that enables the encoding of arbitrary complex-weight networks, providing a direct pathway to uncovering their topological structures. We demonstrate how this quantum approach can identify weighted $k$-cliques and estimate Betti numbers by leveraging the Gaussian boson sampling algorithm's ability to preferentially select high-weight, dense subgraphs. The unique capabilities of our programmable quantum processor allow us to observe topological phase transitions and identify clique percolation phenomena directly from the entropy of the sampling results. These findings showcase how photonic quantum computing can be applied to analyse the topological characteristics of real-world complex networks, opening new possibilities for quantum-enhanced data analysis.

quant-ph↗

arXiv2025

SUSEP-Net: Simulation-Supervised and Contrastive Learning-based Deep Neural Networks for Susceptibility Source Separation

Quantitative susceptibility mapping (QSM) provides a valuable tool for quantifying susceptibility distributions in human brains; however, two types of opposing susceptibility sources (i.e., paramagnetic and diamagnetic), may coexist in a single voxel, and cancel each other out in net QSM images. Susceptibility source separation techniques enable the extraction of sub-voxel information from QSM maps. This study proposes a novel SUSEP-Net for susceptibility source separation by training a dual-branch U-net with a simulation-supervised training strategy. In addition, a contrastive learning framework is included to explicitly impose similarity-based constraints between the branch-specific guidance features in specially-designed encoders and the latent features in the decoders. Comprehensive experiments were carried out on both simulated and in vivo data, including healthy subjects and patients with pathological conditions, to compare SUSEP-Net with three state-of-the-art susceptibility source separation methods (i.e., APART-QSM, \c{hi}-separation, and \c{hi}-sepnet). SUSEP-Net consistently showed improved results compared with the other three methods, with better numerical metrics, improved high-intensity hemorrhage and calcification lesion contrasts, and reduced artifacts in brains with pathological conditions. In addition, experiments on an agarose gel phantom data were conducted to validate the accuracy and the generalization capability of SUSEP-Net.

eess.IV↗

arXiv2025

SUFFICIENT: A scan-specific unsupervised deep learning framework for high-resolution 3D isotropic fetal brain MRI reconstruction

High-quality 3D fetal brain MRI reconstruction from motion-corrupted 2D slices is crucial for clinical diagnosis. Reliable slice-to-volume registration (SVR)-based motion correction and super-resolution reconstruction (SRR) methods are essential. Deep learning (DL) has demonstrated potential in enhancing SVR and SRR when compared to conventional methods. However, it requires large-scale external training datasets, which are difficult to obtain for clinical fetal MRI. To address this issue, we propose an unsupervised iterative SVR-SRR framework for isotropic HR volume reconstruction. Specifically, SVR is formulated as a function mapping a 2D slice and a 3D target volume to a rigid transformation matrix, which aligns the slice to the underlying location in the target volume. The function is parameterized by a convolutional neural network, which is trained by minimizing the difference between the volume slicing at the predicted position and the input slice. In SRR, a decoding network embedded within a deep image prior framework is incorporated with a comprehensive image degradation model to produce the high-resolution (HR) volume. The deep image prior framework offers a local consistency prior to guide the reconstruction of HR volumes. By performing a forward degradation model, the HR volume is optimized by minimizing loss between predicted slices and the observed slices. Comprehensive experiments conducted on large-magnitude motion-corrupted simulation data and clinical data demonstrate the superior performance of the proposed framework over state-of-the-art fetal brain reconstruction frameworks.

eess.IV↗

arXiv2025

Ustnlp16 at SemEval-2025 Task 9: Improving Model Performance through Imbalance Handling and Focal Loss

Classification tasks often suffer from imbal- anced data distribution, which presents chal- lenges in food hazard detection due to severe class imbalances, short and unstructured text, and overlapping semantic categories. In this paper, we present our system for SemEval- 2025 Task 9: Food Hazard Detection, which ad- dresses these issues by applying data augmenta- tion techniques to improve classification perfor- mance. We utilize transformer-based models, BERT and RoBERTa, as backbone classifiers and explore various data balancing strategies, including random oversampling, Easy Data Augmentation (EDA), and focal loss. Our ex- periments show that EDA effectively mitigates class imbalance, leading to significant improve- ments in accuracy and F1 scores. Furthermore, combining focal loss with oversampling and EDA further enhances model robustness, par- ticularly for hard-to-classify examples. These findings contribute to the development of more effective NLP-based classification models for food hazard detection.

cs.CL↗

arXiv2024

A General Framework of Brain Region Detection And Genetic Variants Selection in Imaging Genetics

Imaging genetics is a growing field that employs structural or functional neuroimaging techniques to study individuals with genetic risk variants potentially linked to specific illnesses. This area presents considerable challenges to statisticians due to the heterogeneous information and different data forms it involves. In addition, both imaging and genetic data are typically high-dimensional, creating a "big data squared" problem. Moreover, brain imaging data contains extensive spatial information. Simply vectorizing tensor images and treating voxels as independent features can lead to computational issues and disregard spatial structure. This paper presents a novel statistical method for imaging genetics modeling while addressing all these challenges. We explore a Canonical Correlation Analysis based linear model for the joint modeling of brain imaging, genetic information, and clinical phenotype, enabling the simultaneous detection of significant brain regions and selection of important genetic variants associated with the phenotype outcome. Scalable algorithms are developed to tackle the "big data squared" issue. We apply the proposed method to explore the reaction speed, an indicator of cognitive functions, and its associations with brain MRI and genetic factors using the UK Biobank database. Our study reveals a notable connection between the caudate nucleus region of brain and specific significant SNPs, along with their respective regulated genes, and the reaction speed.

stat.AP↗

arXiv2024

Jointly RS Image Deblurring and Super-Resolution with Adjustable-Kernel and Multi-Domain Attention

Remote Sensing (RS) image deblurring and Super-Resolution (SR) are common tasks in computer vision that aim at restoring RS image detail and spatial scale, respectively. However, real-world RS images often suffer from a complex combination of global low-resolution (LR) degeneration and local blurring degeneration. Although carefully designed deblurring and SR models perform well on these two tasks individually, a unified model that performs jointly RS image deblurring and super-resolution (JRSIDSR) task is still challenging due to the vital dilemma of reconstructing the global and local degeneration simultaneously. Additionally, existing methods struggle to capture the interrelationship between deblurring and SR processes, leading to suboptimal results. To tackle these issues, we give a unified theoretical analysis of RS images' spatial and blur degeneration processes and propose a dual-branch parallel network named AKMD-Net for the JRSIDSR task. AKMD-Net consists of two main branches: deblurring and super-resolution branches. In the deblurring branch, we design a pixel-adjustable kernel block (PAKB) to estimate the local and spatial-varying blur kernels. In the SR branch, a multi-domain attention block (MDAB) is proposed to capture the global contextual information enhanced with high-frequency details. Furthermore, we develop an adaptive feature fusion (AFF) module to model the contextual relationships between the deblurring and SR branches. Finally, we design an adaptive Wiener loss (AW Loss) to depress the prior noise in the reconstructed images. Extensive experiments demonstrate that the proposed AKMD-Net achieves state-of-the-art (SOTA) quantitative and qualitative performance on commonly used RS image datasets. The source code is publicly available at https://github.com/zpc456/AKMD-Net.

cs.CV↗

arXiv2024

Boosting Photon-Number-Resolved Detection Rates of Transition-Edge Sensors by Machine Learning

Transition-Edge Sensors (TESs) are very effective photon-number-resolving (PNR) detectors that have enabled many photonic quantum technologies. However, their relatively slow thermal recovery time severely limits their operation rate in experimental scenarios compared to leading non-PNR detectors. In this work, we develop an algorithmic approach that enables TESs to detect and accurately classify photon pulses without waiting for a full recovery time between detection events. We propose two machine-learning-based signal processing methods: one supervised learning method and one unsupervised clustering method. By benchmarking against data obtained using coherent states and squeezed states, we show that the methods extend the TES operation rate to 800 kHz, achieving at least a four-fold improvement, whilst maintaining accurate photon-number assignment up to at least five photons. Our algorithms will find utility in applications where high rates of PNR detection are required and in technologies which demand fast active feed-forward of PNR detection outcomes.

quant-ph↗

arXiv2024

Shedding Light on the Future: Exploring Quantum Neural Networks through Optics

At the dynamic nexus of artificial intelligence and quantum technology, quantum neural networks (QNNs) play an important role as an emerging technology in the rapidly developing field of quantum machine learning. This development is set to revolutionize the applications of quantum computing. This article reviews the concept of QNNs and their physical realizations, particularly implementations based on quantum optics . We first examine the integration of quantum principles with classical neural network architectures to create QNNs. Some specific examples, such as the quantum perceptron, quantum convolutional neural networks, and quantum Boltzmann machines are discussed. Subsequently, we analyze the feasibility of implementing QNNs through photonics. The key challenge here lies in achieving the required non-linear gates, and measurement-induced approaches, among others, seem promising. To unlock the computational potential of QNNs, addressing the challenge of scaling their complexity through quantum optics is crucial. Progress in controlling quantum states of light is continuously advancing the field. Additionally, we have discovered that different QNN architectures can be unified through non-Gaussian operations. This insight will aid in better understanding and developing more complex QNN circuits.

quant-ph↗

arXiv2024

Time Series Generative Learning with Application to Brain Imaging Analysis

This paper focuses on the analysis of sequential image data, particularly brain imaging data such as MRI, fMRI, CT, with the motivation of understanding the brain aging process and neurodegenerative diseases. To achieve this goal, we investigate image generation in a time series context. Specifically, we formulate a min-max problem derived from the $f$-divergence between neighboring pairs to learn a time series generator in a nonparametric manner. The generator enables us to generate future images by transforming prior lag-k observations and a random vector from a reference distribution. With a deep neural network learned generator, we prove that the joint distribution of the generated sequence converges to the latent truth under a Markov and a conditional invariance condition. Furthermore, we extend our generation mechanism to a panel data scenario to accommodate multiple samples. The effectiveness of our mechanism is evaluated by generating real brain MRI sequences from the Alzheimer's Disease Neuroimaging Initiative. These generated image sequences can be used as data augmentation to enhance the performance of further downstream tasks, such as Alzheimer's disease detection.

stat.ML↗

arXiv2024

A universal programmable Gaussian Boson Sampler for drug discovery

Gaussian Boson Sampling (GBS) exhibits a unique ability to solve graph problems, such as finding cliques in complex graphs. It is noteworthy that many drug discovery tasks can be viewed as the clique-finding process, making them potentially suitable for quantum computation. However, to perform these tasks in their quantum-enhanced form, a large-scale quantum hardware with universal programmability is essential, which is yet to be achieved even with the most advanced GBS devices. Here, we construct a time-bin encoded GBS photonic quantum processor that is universal, programmable, and software-scalable. Our processor features freely adjustable squeezing parameters and can implement arbitrary unitary operations with a programmable interferometer. Using our processor, we have demonstrated the clique-finding task in a 32-node graph, where we found the maximum weighted clique with approximately twice the probability of success compared to classical sampling. Furthermore, a multifunctional quantum pharmaceutical platform is developed. This GBS processor is successfully used to execute two different drug discovery methods, namely molecular docking and RNA folding prediction. Our work achieves the state-of-the-art in GBS circuitry with its distinctive universal and programmable architecture which advances GBS towards real-world applications.

quant-ph↗

arXiv2018

Artificial Intelligent Atomic Force Microscope Enabled by Machine Learning

Artificial intelligence (AI) and machine learning have promised to revolutionize the way we live and work, and one of particularly promising areas for AI is image analysis. Nevertheless, many current AI applications focus on post-processing of data, while in both materials sciences and medicines, it is often critical to respond to the data acquired on the fly. Here we demonstrate an artificial intelligent atomic force microscope (AI-AFM) that is capable of not only pattern recognition and feature identification in ferroelectric materials and electrochemical systems, but can also respond to classification via adaptive experimentation with additional probing at critical domain walls and grain boundaries, all in real time on the fly without human interference. We believe such a strategy empowered by machine learning is applicable to a wide range of instrumentations and broader physical machineries.

cond-mat.mtrl-sci↗