arXiv subjects

Yuxi Liu

Publications and source records attributed to Yuxi Liu.

At least 55 records · Page 3Linked to original sources

arXiv2025

Efficiently Laser Driven Terahertz Surface Plasmon Polaritons on Long Metal Wire

We experimentally demonstrate a novel scheme for efficiently generating intense terahertz (THz) surface plasmon polaritons (SPPs) on a sub-wavelength-diameter meter-long metal wire. Driven by a subrelativistic femtosecond laser (a0=0.3, 3 mJ) focused at the wire's midpoint, single-cycle ten-megawatt THz SPPs are excited and propagating bidirectionally along it over 25 cm. The measured laser-to-SPPs energy conversion efficiency is reaching up to ~2.4%, which is the highest value at present. It is proved that the THz SPPs are excited by coherent transition radiation of the subrelativistic laser produced escaping electrons. Particle-in-cell together with CST simulations confirm the experimental observations. Our scheme of using readily available subrelativistic laser should thus be useful to applications requiring terawatt level single-cycle THz SPPs.

physics.optics↗

arXiv2024

CrypQ: A Database Benchmark Based on Dynamic, Ever-Evolving Ethereum Data

Modern database systems are expected to handle dynamic data whose characteristics may evolve over time. Many popular database benchmarks are limited in their ability to evaluate this dynamic aspect of the database systems. Those that use synthetic data generators often fail to capture the complexity and unpredictable nature of real data, while most real-world datasets are static and difficult to create high-volume, realistic updates for. This paper introduces CrypQ, a database benchmark leveraging dynamic, public Ethereum blockchain data. CrypQ offers a high-volume, ever-evolving dataset reflecting the unpredictable nature of a real and active cryptocurrency market. We detail CrypQ's schema, procedures for creating data snapshots and update sequences, and a suite of relevant SQL queries. As an example, we demonstrate CrypQ's utility in evaluating cost-based query optimizers on complex, evolving data distributions with real-world skewness and dependencies.

cs.DB↗

arXiv2024

FedFMS: Exploring Federated Foundation Models for Medical Image Segmentation

Medical image segmentation is crucial for clinical diagnosis. The Segmentation Anything Model (SAM) serves as a powerful foundation model for visual segmentation and can be adapted for medical image segmentation. However, medical imaging data typically contain privacy-sensitive information, making it challenging to train foundation models with centralized storage and sharing. To date, there are few foundation models tailored for medical image deployment within the federated learning framework, and the segmentation performance, as well as the efficiency of communication and training, remain unexplored. In response to these issues, we developed Federated Foundation models for Medical image Segmentation (FedFMS), which includes the Federated SAM (FedSAM) and a communication and training-efficient Federated SAM with Medical SAM Adapter (FedMSA). Comprehensive experiments on diverse datasets are conducted to investigate the performance disparities between centralized training and federated learning across various configurations of FedFMS. The experiments revealed that FedFMS could achieve performance comparable to models trained via centralized training methods while maintaining privacy. Furthermore, FedMSA demonstrated the potential to enhance communication and training efficiency. Our model implementation codes are available at https://github.com/LIU-YUXI/FedFMS.

eess.IV↗

arXiv2024

The Cost of Representation by Subset Repairs

Datasets may include errors, and specifically violations of integrity constraints, for various reasons. Standard techniques for ``minimal-cost'' database repairing resolve these violations by aiming for minimum change in the data, and in the process, may sway representations of different sub-populations. For instance, the repair may end up deleting more females than males, or more tuples from a certain age group or race, due to varying levels of inconsistency in different sub-populations. Such repaired data can mislead consumers when used for analytics, and can lead to biased decisions for downstream machine learning tasks. We study the ``cost of representation'' in subset repairs for functional dependencies. In simple terms, we target the question of how many additional tuples have to be deleted if we want to satisfy not only the integrity constraints but also representation constraints for given sub-populations. We study the complexity of this problem and compare it with the complexity of optimal subset repairs without representations. While the problem is NP-hard in general, we give polynomial-time algorithms for special cases, and efficient heuristics for general cases. We perform a suite of experiments that show the effectiveness of our algorithms in computing or approximating the cost of representation.

cs.DB↗

arXiv2024

Region-Adaptive Transform with Segmentation Prior for Image Compression

Learned Image Compression (LIC) has shown remarkable progress in recent years. Existing works commonly employ CNN-based or self-attention-based modules as transform methods for compression. However, there is no prior research on neural transform that focuses on specific regions. In response, we introduce the class-agnostic segmentation masks (i.e. semantic masks without category labels) for extracting region-adaptive contextual information. Our proposed module, Region-Adaptive Transform, applies adaptive convolutions on different regions guided by the masks. Additionally, we introduce a plug-and-play module named Scale Affine Layer to incorporate rich contexts from various regions. While there have been prior image compression efforts that involve segmentation masks as additional intermediate inputs, our approach differs significantly from them. Our advantages lie in that, to avoid extra bitrate overhead, we treat these masks as privilege information, which is accessible during the model training stage but not required during the inference phase. To the best of our knowledge, we are the first to employ class-agnostic masks as privilege information and achieve superior performance in pixel-fidelity metrics, such as Peak Signal to Noise Ratio (PSNR). The experimental results demonstrate our improvement compared to previously well-performing methods, with about 8.2% bitrate saving compared to VTM-17.0. The source code is available at https://github.com/GityuxiLiu/SegPIC-for-Image-Compression.

cs.CV↗

arXiv2024

Quantum wavepackets: Proofs (almost) without words

We present a geometrical way of understanding the dynamics of wavefunctions in a free space, using the phase-space formulation of quantum mechanics. By visualizing the Wigner function, the spreading, shearing, the so-called "negative probability flow" of wavefunctions, and the long-time asymptotic dispersion, are intuited visually. These results are not new, but previous derivations were analytical, whereas this paper presents elementary geometric arguments that are almost "proofs without words", and suitable for a first course in quantum mechanics.

quant-ph↗

arXiv2024

Solving Co-Path/Cycle Packing and Co-Path Packing Faster Than $3^k$

The \textsc{Co-Path/Cycle Packing} problem (resp. The \textsc{Co-Path Packing} problem) asks whether we can delete at most $k$ vertices from the input graph such that the remaining graph is a collection of induced paths and cycles (resp. induced paths). These two problems are fundamental graph problems that have important applications in bioinformatics. Although these two problems have been extensively studied in parameterized algorithms, it seems hard to break the running time bound $3^k$. In 2015, Feng et al. provided an $O^*(3^k)$-time randomized algorithms for both of them. Recently, Tsur showed that they can be solved in $O^*(3^k)$ time deterministically. In this paper, by combining several techniques such as path decomposition, dynamic programming, cut \& count, and branch-and-search methods, we show that \textsc{Co-Path/Cycle Packing} can be solved in $O^*(2.8192^k)$ time deterministically and \textsc{Co-Path Packing} can be solved in $O^*(2.9241^{k})$ time with failure probability $\leq 1/3$. As a by-product, we also show that the \textsc{Co-Path Packing} problem can be solved in $O^*(5^p)$ time with probability at least 2/3 if a path decomposition of width $p$ is given.

cs.DS↗

arXiv2024

SelfGNN: Self-Supervised Graph Neural Networks for Sequential Recommendation

Sequential recommendation effectively addresses information overload by modeling users' temporal and sequential interaction patterns. To overcome the limitations of supervision signals, recent approaches have adopted self-supervised learning techniques in recommender systems. However, there are still two critical challenges that remain unsolved. Firstly, existing sequential models primarily focus on long-term modeling of individual interaction sequences, overlooking the valuable short-term collaborative relationships among the behaviors of different users. Secondly, real-world data often contain noise, particularly in users' short-term behaviors, which can arise from temporary intents or misclicks. Such noise negatively impacts the accuracy of both graph and sequence models, further complicating the modeling process. To address these challenges, we propose a novel framework called Self-Supervised Graph Neural Network (SelfGNN) for sequential recommendation. The SelfGNN framework encodes short-term graphs based on time intervals and utilizes Graph Neural Networks (GNNs) to learn short-term collaborative relationships. It captures long-term user and item representations at multiple granularity levels through interval fusion and dynamic behavior modeling. Importantly, our personalized self-augmented learning structure enhances model robustness by mitigating noise in short-term graphs based on long-term user interests and personal stability. Extensive experiments conducted on four real-world datasets demonstrate that SelfGNN outperforms various state-of-the-art baselines. Our model implementation codes are available at https://github.com/HKUDS/SelfGNN.

cs.IR↗

arXiv2024

An Improved Kernel and Parameterized Algorithm for Almost Induced Matching

An induced subgraph is called an induced matching if each vertex is a degree-1 vertex in the subgraph. The \textsc{Almost Induced Matching} problem asks whether we can delete at most $k$ vertices from the input graph such that the remaining graph is an induced matching. This paper studies parameterized algorithms for this problem by taking the size $k$ of the deletion set as the parameter. First, we prove a $6k$-vertex kernel for this problem, improving the previous result of $7k$. Second, we give an $O^*(1.6765^k)$-time and polynomial-space algorithm, improving the previous running-time bound of $O^*(1.7485^k)$.

cs.DS↗

arXiv2023

Temporal Interaction -- Bridging Time and Experience in Human-Computer Interaction

Traditional static user interfaces (UI) have given way to dynamic systems that can intelligently adapt to and respond to users' changing needs. Temporal interaction is an emerging field in human-computer interaction (HCI), which refers to the study and design of UI that are capable of adapting and responding to the user's changing behavioral and emotional states. By comprehending and incorporating the temporal component of user interactions, it focuses on developing dynamic and individualized user experiences. This idea places a strong emphasis on the value of adjusting to user behavior and emotions in order to create a more unique and interesting user experience. The potential of temporal interaction to alter user interface design is highlighted by this paper's examination of its capacity to adjust to user behavior and react to emotional states. Designers can create interfaces that respond to the changing demands, emotions, and behaviors of users by utilizing temporal interactions. This produces interfaces that are not only highly functional but also form an emotional connection with the users.

cs.HC↗

arXiv2023

Hypergraph Convolutional Networks for Fine-grained ICU Patient Similarity Analysis and Risk Prediction

The Intensive Care Unit (ICU) is one of the most important parts of a hospital, which admits critically ill patients and provides continuous monitoring and treatment. Various patient outcome prediction methods have been attempted to assist healthcare professionals in clinical decision-making. Existing methods focus on measuring the similarity between patients using deep neural networks to capture the hidden feature structures. However, the higher-order relationships are ignored, such as patient characteristics (e.g., diagnosis codes) and their causal effects on downstream clinical predictions. In this paper, we propose a novel Hypergraph Convolutional Network that allows the representation of non-pairwise relationships among diagnosis codes in a hypergraph to capture the hidden feature structures so that fine-grained patient similarity can be calculated for personalized mortality risk prediction. Evaluation using a publicly available eICU Collaborative Research Database indicates that our method achieves superior performance over the state-of-the-art models on mortality risk prediction. Moreover, the results of several case studies demonstrated the effectiveness and robustness of the model decisions.

cs.LG↗

arXiv2023

BCGGAN: Ballistocardiogram artifact removal in simultaneous EEG-fMRI using generative adversarial network

Due to its advantages of high temporal and spatial resolution, the technology of simultaneous electroencephalogram-functional magnetic resonance imaging (EEG-fMRI) acquisition and analysis has attracted much attention, and has been widely used in various research fields of brain science. However, during the fMRI of the brain, ballistocardiogram (BCG) artifacts can seriously contaminate the EEG. As an unpaired problem, BCG artifact removal now remains a considerable challenge. Aiming to provide a solution, this paper proposed a novel modular generative adversarial network (GAN) and corresponding training strategy to improve the network performance by optimizing the parameters of each module. In this manner, we hope to improve the local representation ability of the network model, thereby improving its overall performance and obtaining a reliable generator for BCG artifact removal. Moreover, the proposed method does not rely on additional reference signal or complex hardware equipment. Experimental results show that, compared with multiple methods, the technique presented in this paper can remove the BCG artifact more effectively while retaining essential EEG information.

cs.LG↗

arXiv2023

Contrastive Learning-based Imputation-Prediction Networks for In-hospital Mortality Risk Modeling using EHRs

Predicting the risk of in-hospital mortality from electronic health records (EHRs) has received considerable attention. Such predictions will provide early warning of a patient's health condition to healthcare professionals so that timely interventions can be taken. This prediction task is challenging since EHR data are intrinsically irregular, with not only many missing values but also varying time intervals between medical records. Existing approaches focus on exploiting the variable correlations in patient medical records to impute missing values and establishing time-decay mechanisms to deal with such irregularity. This paper presents a novel contrastive learning-based imputation-prediction network for predicting in-hospital mortality risks using EHR data. Our approach introduces graph analysis-based patient stratification modeling in the imputation process to group similar patients. This allows information of similar patients only to be used, in addition to personal contextual information, for missing value imputation. Moreover, our approach can integrate contrastive learning into the proposed network architecture to enhance patient representation learning and predictive performance on the classification task. Experiments on two real-world EHR datasets show that our approach outperforms the state-of-the-art approaches in both imputation and prediction tasks.

cs.LG↗

arXiv2023

Hydrogels enable negative pressure in water for efficient heat utilization and transfer

Metastable water in negative pressure can provide giant passive driving pressure up to several megapascals for efficient evaporation-driven flow, however, the practical applications with negative pressure are rare due to the challenges of generating and maintaining large negative pressure. In this work, we report a novel structure with thin hydrogel films as evaporation surfaces and robust porous substrates as the supports, and obtain a high negative pressure of -1.61 MPa through water evaporation. Molecular dynamics simulations elucidate the essential role of strong interaction between water molecules and polymer chains in generating the negative pressure. With such a large negative pressure, we demonstrate a streaming potential generator that spontaneously converts environmental energy into electricity and outputs a voltage of 1.06 V. Moreover, we propose a "negative pressure heat pipe" for the first time, which achieves a high heat transfer density of 11.2 kW cm-2 with a flow length of 1 m, showing the potential of negative pressure in efficient heat utilization and transfer.

physics.chem-ph↗

arXiv2022

Integrated Convolutional and Recurrent Neural Networks for Health Risk Prediction using Patient Journey Data with Many Missing Values

Predicting the health risks of patients using Electronic Health Records (EHR) has attracted considerable attention in recent years, especially with the development of deep learning techniques. Health risk refers to the probability of the occurrence of a specific health outcome for a specific patient. The predicted risks can be used to support decision-making by healthcare professionals. EHRs are structured patient journey data. Each patient journey contains a chronological set of clinical events, and within each clinical event, there is a set of clinical/medical activities. Due to variations of patient conditions and treatment needs, EHR patient journey data has an inherently high degree of missingness that contains important information affecting relationships among variables, including time. Existing deep learning-based models generate imputed values for missing values when learning the relationships. However, imputed data in EHR patient journey data may distort the clinical meaning of the original EHR patient journey data, resulting in classification bias. This paper proposes a novel end-to-end approach to modeling EHR patient journey data with Integrated Convolutional and Recurrent Neural Networks. Our model can capture both long- and short-term temporal patterns within each patient journey and effectively handle the high degree of missingness in EHR data without any imputation data generation. Extensive experimental results using the proposed model on two real-world datasets demonstrate robust performance as well as superior prediction accuracy compared to existing state-of-the-art imputation-based prediction methods.

cs.LG↗

arXiv2022

Compound Density Networks for Risk Prediction using Electronic Health Records

Electronic Health Records (EHRs) exhibit a high amount of missing data due to variations of patient conditions and treatment needs. Imputation of missing values has been considered an effective approach to deal with this challenge. Existing work separates imputation method and prediction model as two independent parts of an EHR-based machine learning system. We propose an integrated end-to-end approach by utilizing a Compound Density Network (CDNet) that allows the imputation method and prediction model to be tuned together within a single framework. CDNet consists of a Gated recurrent unit (GRU), a Mixture Density Network (MDN), and a Regularized Attention Network (RAN). The GRU is used as a latent variable model to model EHR data. The MDN is designed to sample latent variables generated by GRU. The RAN serves as a regularizer for less reliable imputed values. The architecture of CDNet enables GRU and MDN to iteratively leverage the output of each other to impute missing values, leading to a more accurate and robust prediction. We validate CDNet on the mortality prediction task on the MIMIC-III dataset. Our model outperforms state-of-the-art models by significant margins. We also empirically show that regularizing imputed values is a key factor for superior prediction performance. Analysis of prediction uncertainty shows that our model can capture both aleatoric and epistemic uncertainties, which offers model users a better understanding of the model results.

cs.LG↗

arXiv2022

Modeling Long-term Dependencies and Short-term Correlations in Patient Journey Data with Temporal Attention Networks for Health Prediction

Building models for health prediction based on Electronic Health Records (EHR) has become an active research area. EHR patient journey data consists of patient time-ordered clinical events/visits from patients. Most existing studies focus on modeling long-term dependencies between visits, without explicitly taking short-term correlations between consecutive visits into account, where irregular time intervals, incorporated as auxiliary information, are fed into health prediction models to capture latent progressive patterns of patient journeys. We present a novel deep neural network with four modules to take into account the contributions of various variables for health prediction: i) the Stacked Attention module strengthens the deep semantics in clinical events within each patient journey and generates visit embeddings, ii) the Short-Term Temporal Attention module models short-term correlations between consecutive visit embeddings while capturing the impact of time intervals within those visit embeddings, iii) the Long-Term Temporal Attention module models long-term dependencies between visit embeddings while capturing the impact of time intervals within those visit embeddings, iv) and finally, the Coupled Attention module adaptively aggregates the outputs of Short-Term Temporal Attention and Long-Term Temporal Attention modules to make health predictions. Experimental results on MIMIC-III demonstrate superior predictive accuracy of our model compared to existing state-of-the-art methods, as well as the interpretability and robustness of this approach. Furthermore, we found that modeling short-term correlations contributes to local priors generation, leading to improved predictive modeling of patient journeys.

cs.LG↗

arXiv2022

Utilizing Parallelism in Smart Contracts on Decentralized Blockchains by Taming Application-Inherent Conflicts

Traditional public blockchain systems typically had very limited transaction throughput because of the bottleneck of the consensus protocol itself. With recent advances in consensus technology, the performance limit has been greatly lifted, typically to thousands of transactions per second. With this, transaction execution has become a new performance bottleneck. Exploiting parallelism in transaction execution is a clear and direct way to address this and to further increase transaction throughput. Although some recent literature introduced concurrency control mechanisms to execute smart contract transactions in parallel, the reported speedup that they can achieve is far from ideal. The main reason is that the proposed parallel execution mechanisms cannot effectively deal with the conflicts inherent in many blockchain applications. In this work, we thoroughly study the historical transaction execution traces in Ethereum. We observe that application-inherent conflicts are the major factors that limit the exploitable parallelism during execution. We propose to use partitioned counters and special commutative instructions to break up the application conflict chains in order to maximize the potential speedup. When we evaluated the maximum parallel speedup achievable, these techniques doubled this limit to an 18x overall speedup compared to serial execution, thus approaching the optimum. We also propose OCC-DA, an optimistic concurrency control scheduler with deterministic aborts, which makes it possible to use OCC scheduling in public blockchain settings.

cs.DC↗