arXiv subjects

Xinyue Wang

Publications and source records attributed to Xinyue Wang.

54 records · Page 3Linked to original sources

arXiv2025

An Optimization Algorithm for Multimodal Data Alignment

In the data era, the integration of multiple data types, known as multimodality, has become a key area of interest in the research community. This interest is driven by the goal to develop cutting edge multimodal models capable of serving as adaptable reasoning engines across a wide range of modalities and domains. Despite the fervent development efforts, the challenge of optimally representing different forms of data within a single unified latent space a crucial step for enabling effective multimodal reasoning has not been fully addressed. To bridge this gap, we introduce AlignXpert, an optimization algorithm inspired by Kernel CCA crafted to maximize the similarities between N modalities while imposing some other constraints. This work demonstrates the impact on improving data representation for a variety of reasoning tasks, such as retrieval and classification, underlining the pivotal importance of data representation.

cs.LG↗

arXiv2025

Internal Heat and Energy Imbalance of Uranus

With its extreme axial tilt, radiant energy budget and internal heat of Uranus remain among the most intriguing mysteries of our Solar System. Here, we present the global radiant energy budget spanning a complete orbital period, revealing significant seasonal variations driven primarily by the highly variable solar flux. Despite these fluctuations, emitted thermal power consistently exceeds absorbed solar power, indicating a net energy loss and ongoing global cooling. Based on the seasonal variations of radiant energy budget, we determine a statistically significant internal heat flux. This finding resolves a long-standing debate over whether Uranus possesses internal heat. We also examine the energy budget of the weather layer by combining the internal heat with the radiant energies, revealing significant energy imbalances at both global and hemispheric scales. These global and hemispheric imbalances should be considered in theoretical and numerical models. The Uranus flagship mission, as recommended by the recent survey, will provide crucial observations to address more unresolved questions and advance our understanding of this enigmatic ice giant.

astro-ph.EP↗

arXiv2025

A Python Toolkit for Plotting Double Star Observations with 1:1 Aspect Ratio

Accurate visualization of double star astrometric data is essential for effective analysis and interpretation. This article presents a Python toolkit designed for astronomers who need to plot measurements from diverse sources -- historical, Gaia DR3, and the Las Cumbres Observatory (LCO) network -- while maintaining a 1:1 aspect ratio to avoid visually distorting the data. The toolkit is composed of three scripts: one that handles polar coordinates (P.A., separation), one for Cartesian (X, Y) coordinates, and another with the option to include predicted theoretical points. This paper describes the purpose, functionality, and usage of these scripts, including example figures, installation guides, and licensing information. This toolkit has been used by the author and collaborators in published and submitted research on double star systems, demonstrating its versatility for both professional and student-driven investigations.

astro-ph.IM↗

arXiv2024

SAKA: An Intelligent Platform for Semi-automated Knowledge Graph Construction and Application

Knowledge graph (KG) technology is extensively utilized in many areas, and many companies offer applications based on KG. Nonetheless, most KG platforms necessitate expertise and tremendous time and effort from users to construct KG records manually, which poses great difficulties for ordinary people. Additionally, audio data is abundant and holds valuable information, but it is challenging to transform it into a KG. What's more, the platforms usually do not leverage the full potential of the KGs constructed by users. In this paper, we propose an intelligent and user-friendly platform for Semi-automated KG Construction and Application (SAKA) to address the aforementioned problems. Primarily, users can semi-automatically construct KGs from structured data of numerous areas by interacting with the platform, based on which multi-versions of KG can be stored, viewed, managed, and updated. Moreover, we propose an Audio-based KG Information Extraction (AGIE) method to establish KGs from audio data. Lastly, the platform creates a semantic parsing-based knowledge base question answering (KBQA) system based on the user-created KGs. We prove the feasibility of the semi-automatic KG construction method on the SAKA platform.

cs.AI↗

arXiv2024

SimpleFusion: A Simple Fusion Framework for Infrared and Visible Images

Integrating visible and infrared images into one high-quality image, also known as visible and infrared image fusion, is a challenging yet critical task for many downstream vision tasks. Most existing works utilize pretrained deep neural networks or design sophisticated frameworks with strong priors for this task, which may be unsuitable or lack flexibility. This paper presents SimpleFusion, a simple yet effective framework for visible and infrared image fusion. Our framework follows the decompose-and-fusion paradigm, where the visible and the infrared images are decomposed into reflectance and illumination components via Retinex theory and followed by the fusion of these corresponding elements. The whole framework is designed with two plain convolutional neural networks without downsampling, which can perform image decomposition and fusion efficiently. Moreover, we introduce decomposition loss and a detail-to-semantic loss to preserve the complementary information between the two modalities for fusion. We conduct extensive experiments on the challenging benchmarks, verifying the superiority of our method over previous state-of-the-arts. Code is available at \href{https://github.com/hxwxss/SimpleFusion-A-Simple-Fusion-Framework-for-Infrared-and-Visible-Images}{https://github.com/hxwxss/SimpleFusion-A-Simple-Fusion-Framework-for-Infrared-and-Visible-Images}

cs.CV↗

arXiv2023

Learning domain-specific causal discovery from time series

Causal discovery (CD) from time-varying data is important in neuroscience, medicine, and machine learning. Techniques for CD encompass randomized experiments, which are generally unbiased but expensive, and algorithms such as Granger causality, conditional-independence-based, structural-equation-based, and score-based methods that are only accurate under strong assumptions made by human designers. However, as demonstrated in other areas of machine learning, human expertise is often not entirely accurate and tends to be outperformed in domains with abundant data. In this study, we examine whether we can enhance domain-specific causal discovery for time series using a data-driven approach. Our findings indicate that this procedure significantly outperforms human-designed, domain-agnostic causal discovery methods, such as Mutual Information, VAR-LiNGAM, and Granger Causality on the MOS 6502 microprocessor, the NetSim fMRI dataset, and the Dream3 gene dataset. We argue that, when feasible, the causality field should consider a supervised approach in which domain-specific CD procedures are learned from extensive datasets with known causal relationships, rather than being designed by human specialists. Our findings promise a new approach toward improving CD in neural and medical data and for the broader machine learning community.

cs.LG↗

arXiv2023

Observation of zero resistance above 100$^\circ$ K in Pb$_{10-x}$Cu$_x$(PO$_4$)$_6$O

Room-temperature superconductivity has always been regarded as the ultimate goal in the fields of solid-state physics and materials science, with its realization holding revolutionary significance, capable of triggering significant changes in energy transmission and storage. However, achieving it poses various challenges. Recent research revealed that material Pb$_{10-x}$Cu$_x$(PO$_4$)$_6$O displays room-temperature superconductivity under atmospheric pressure, sparking global interest in further exploration. Here, we utilized solid-phase synthesis to obtain a polycrystalline sample of Pb$_{10-x}$Cu$_x$(PO$_4$)$_6$O. X-ray diffraction confirmed its structural consistency with referenced literature. Zero resistance, which is important evidence for superconductivity, was observed above 100$^\circ$ K under ambient pressure in our experiment. Our finding indicates that Pb$_{10-x}$Cu$_x$(PO$_4$)$_6$O is a possible candidate for searching high-temperature superconductors.

cond-mat.supr-con↗

arXiv2023

X-MLP: A Patch Embedding-Free MLP Architecture for Vision

Convolutional neural networks (CNNs) and vision transformers (ViT) have obtained great achievements in computer vision. Recently, the research of multi-layer perceptron (MLP) architectures for vision have been popular again. Vision MLPs are designed to be independent from convolutions and self-attention operations. However, existing vision MLP architectures always depend on convolution for patch embedding. Thus we propose X-MLP, an architecture constructed absolutely upon fully connected layers and free from patch embedding. It decouples the features extremely and utilizes MLPs to interact the information across the dimension of width, height and channel independently and alternately. X-MLP is tested on ten benchmark datasets, all obtaining better performance than other vision MLP models. It even surpasses CNNs by a clear margin on various dataset. Furthermore, through mathematically restoring the spatial weights, we visualize the information communication between any couples of pixels in the feature map and observe the phenomenon of capturing long-range dependency.

cs.CV↗

arXiv2023

Iterative-in-Iterative Super-Resolution Biomedical Imaging Using One Real Image

Deep learning-based super-resolution models have the potential to revolutionize biomedical imaging and diagnoses by effectively tackling various challenges associated with early detection, personalized medicine, and clinical automation. However, the requirement of an extensive collection of high-resolution images presents limitations for widespread adoption in clinical practice. In our experiment, we proposed an approach to effectively train the deep learning-based super-resolution models using only one real image by leveraging self-generated high-resolution images. We employed a mixed metric of image screening to automatically select images with a distribution similar to ground truth, creating an incrementally curated training data set that encourages the model to generate improved images over time. After five training iterations, the proposed deep learning-based super-resolution model experienced a 7.5\% and 5.49\% improvement in structural similarity and peak-signal-to-noise ratio, respectively. Significantly, the model consistently produces visually enhanced results for training, improving its performance while preserving the characteristics of original biomedical images. These findings indicate a potential way to train a deep neural network in a self-revolution manner independent of real-world human data.

physics.med-ph↗

arXiv2023

Recognizable Information Bottleneck

Information Bottlenecks (IBs) learn representations that generalize to unseen data by information compression. However, existing IBs are practically unable to guarantee generalization in real-world scenarios due to the vacuous generalization bound. The recent PAC-Bayes IB uses information complexity instead of information compression to establish a connection with the mutual information generalization bound. However, it requires the computation of expensive second-order curvature, which hinders its practical application. In this paper, we establish the connection between the recognizability of representations and the recent functional conditional mutual information (f-CMI) generalization bound, which is significantly easier to estimate. On this basis we propose a Recognizable Information Bottleneck (RIB) which regularizes the recognizability of representations through a recognizability critic optimized by density ratio matching under the Bregman divergence. Extensive experiments on several commonly used datasets demonstrate the effectiveness of the proposed method in regularizing the model and estimating the generalization gap.

cs.LG↗

arXiv2023

Look-Ahead AC Optimal Power Flow: A Model-Informed Reinforcement Learning Approach

With the increasing proportion of renewable energy in the generation side, it becomes more difficult to accurately predict the power generation and adapt to the large deviations between the optimal dispatch scheme and the day-ahead scheduling in the process of real-time dispatch. Therefore, it is necessary to conduct look-ahead dispatches to revise the operation plan according to the real-time status of the power grid and reliable ultra-short-term prediction. Application of traditional model-driven methods is often limited by the scale of the power system and cannot meet the computational time requirements of real-time dispatch. Data-driven methods can provide strong online decision-making support abilities when facing large-scale systems, while it is limited by the quantity and quality of the training dataset. This paper proposes a model-informed reinforcement learning approach for look-ahead AC optimal power flow. The reinforcement learning model is first formulated based on the domain knowledge of economic dispatch, and then the physics-informed neural network is constructed to enhance the reliability and efficiency. At last, the case study based on the SG 126-bus system validates the accuracy and efficiency of the proposed approach.

eess.SY↗

arXiv2022

Neural Networks as Paths through the Space of Representations

Deep neural networks implement a sequence of layer-by-layer operations that are each relatively easy to understand, but the resulting overall computation is generally difficult to understand. We consider a simple hypothesis for interpreting the layer-by-layer construction of useful representations: perhaps the role of each layer is to reformat information to reduce the "distance" to the desired outputs. With this framework, the layer-wise computation implemented by a deep neural network can be viewed as a path through a high-dimensional representation space. We formalize this intuitive idea of a "path" by leveraging recent advances in *metric* representational similarity. We extend existing representational distance methods by computing geodesics, angles, and projections of representations, going beyond mere layer distances. We then demonstrate these tools by visualizing and comparing the paths taken by ResNet and VGG architectures on CIFAR-10. We conclude by sketching additional ways that this kind of representational geometry can be used to understand and interpret network training, and to describe novel kinds of similarities between different models.

cs.LG↗

arXiv2022

Evaluation of Look-ahead Economic Dispatch Using Reinforcement Learning

Modern power systems are experiencing a variety of challenges driven by renewable energy, which calls for developing novel dispatch methods such as reinforcement learning (RL). Evaluation of these methods as well as the RL agents are largely under explored. In this paper, we propose an evaluation approach to analyze the performance of RL agents in a look-ahead economic dispatch scheme. This approach is conducted by scanning multiple operational scenarios. In particular, a scenario generation method is developed to generate the network scenarios and demand scenarios for evaluation, and network structures are aggregated according to the change rates of power flow. Then several metrics are defined to evaluate the agents' performance from the perspective of economy and security. In the case study, we use a modified IEEE 30-bus system to illustrate the effectiveness of the proposed evaluation approach, and the simulation results reveal good and rapid adaptation to different scenarios. The comparison between different RL agents is also informative to offer advice for a better design of the learning strategies.

eess.SY↗

arXiv2022

Facilitating Federated Genomic Data Analysis by Identifying Record Correlations while Ensuring Privacy

With the reduction of sequencing costs and the pervasiveness of computing devices, genomic data collection is continually growing. However, data collection is highly fragmented and the data is still siloed across different repositories. Analyzing all of this data would be transformative for genomics research. However, the data is sensitive, and therefore cannot be easily centralized. Furthermore, there may be correlations in the data, which if not detected, can impact the analysis. In this paper, we take the first step towards identifying correlated records across multiple data repositories in a privacy-preserving manner. The proposed framework, based on random shuffling, synthetic record generation, and local differential privacy, allows a trade-off of accuracy and computational efficiency. An extensive evaluation on real genomic data from the OpenSNP dataset shows that the proposed solution is efficient and effective.

cs.CR↗

arXiv2021

Cardiac Segmentation on Late Gadolinium Enhancement MRI: A Benchmark Study from Multi-Sequence Cardiac MR Segmentation Challenge

Accurate computing, analysis and modeling of the ventricles and myocardium from medical images are important, especially in the diagnosis and treatment management for patients suffering from myocardial infarction (MI). Late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) provides an important protocol to visualize MI. However, automated segmentation of LGE CMR is still challenging, due to the indistinguishable boundaries, heterogeneous intensity distribution and complex enhancement patterns of pathological myocardium from LGE CMR. Furthermore, compared with the other sequences LGE CMR images with gold standard labels are particularly limited, which represents another obstacle for developing novel algorithms for automatic segmentation of LGE CMR. This paper presents the selective results from the Multi-Sequence Cardiac MR (MS-CMR) Segmentation challenge, in conjunction with MICCAI 2019. The challenge offered a data set of paired MS-CMR images, including auxiliary CMR sequences as well as LGE CMR, from 45 patients who underwent cardiomyopathy. It was aimed to develop new algorithms, as well as benchmark existing ones for LGE CMR segmentation and compare them objectively. In addition, the paired MS-CMR images could enable algorithms to combine the complementary information from the other sequences for the segmentation of LGE CMR. Nine representative works were selected for evaluation and comparisons, among which three methods are unsupervised methods and the other six are supervised. The results showed that the average performance of the nine methods was comparable to the inter-observer variations. The success of these methods was mainly attributed to the inclusion of the auxiliary sequences from the MS-CMR images, which provide important label information for the training of deep neural networks.

eess.IV↗

arXiv2020

The Case For Alternative Web Archival Formats To Expedite The Data-To-Insight Cycle

The WARC file format is widely used by web archives to preserve collected web content for future use. With the rapid growth of web archives and the increasing interest to reuse these archives as big data sources for statistical and analytical research, the speed to turn these data into insights becomes critical. In this paper we show that the WARC format carries significant performance penalties for batch processing workload. We trace the root cause of these penalties to its data structure, encoding, and addressing method. We then run controlled experiments to illustrate how severe these problems can be. Indeed, performance gain of one to two orders of magnitude can be achieved simply by reformatting WARC files into Parquet or Avro formats. While these results do not necessarily constitute an endorsement for Avro or Parquet, the time has come for the web archiving community to consider replacing WARC with more efficient web archival formats.

cs.DL↗

arXiv2019

Cantonese Automatic Speech Recognition Using Transfer Learning from Mandarin

We propose a system to develop a basic automatic speech recognizer(ASR) for Cantonese, a low-resource language, through transfer learning of Mandarin, a high-resource language. We take a time-delayed neural network trained on Mandarin, and perform weight transfer of several layers to a newly initialized model for Cantonese. We experiment with the number of layers transferred, their learning rates, and pretraining i-vectors. Key findings are that this approach allows for quicker training time with less data. We find that for every epoch, log-probability is smaller for transfer learning models compared to a Cantonese-only model. The transfer learning models show slight improvement in CER.

cs.CL↗

arXiv2018

Probabilistic Re-aggregation Algorithm [First Draft]

Spatial data about individuals or businesses is often aggregated over polygonal regions to preserve privacy, provide useful insight and support decision making. Given a particular aggregation of data (say into local government areas), the re-aggregation problem is to estimate how that same data would aggregate over a different set of polygonal regions (say electorates) without having access to the original unit records. Data61 is developing new re-aggregation algorithms that both estimate confidence intervals of their predictions and utilize additional related datasets when available to improve accuracy. The algorithms are an improvement over the current re-aggregation procedure in use by the ABS, which is manually applied by the data user, less accurate in validation experiments and provides a single best guess answer. The algorithms are deployed in an accessible web service that automatically learns a model and applies it to user-data. This report formulates the re-aggregation problem, describes Data61's new algorithms, and presents preliminary validation experiments.

stat.AP↗