Searcharxiv⌕ Search

arXiv subjects

Nan Liu

Publications and source records attributed to Nan Liu.

At least 109 records · Page 6Linked to original sources
arXiv2023

Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models

Text-to-image generative models have enabled high-resolution image synthesis across different domains, but require users to specify the content they wish to generate. In this paper, we consider the inverse problem -- given a collection of different images, can we discover the generative concepts that represent each image? We present an unsupervised approach to discover generative concepts from a collection of images, disentangling different art styles in paintings, objects, and lighting from kitchen scenes, and discovering image classes given ImageNet images. We show how such generative concepts can accurately represent the content of images, be recombined and composed to generate new artistic and hybrid images, and be further used as a representation for downstream classification tasks.

cs.CV↗
arXiv2023

Towards clinical AI fairness: A translational perspective

Artificial intelligence (AI) has demonstrated the ability to extract insights from data, but the issue of fairness remains a concern in high-stakes fields such as healthcare. Despite extensive discussion and efforts in algorithm development, AI fairness and clinical concerns have not been adequately addressed. In this paper, we discuss the misalignment between technical and clinical perspectives of AI fairness, highlight the barriers to AI fairness' translation to healthcare, advocate multidisciplinary collaboration to bridge the knowledge gap, and provide possible solutions to address the clinical concerns pertaining to AI fairness.

cs.CY↗
arXiv2023

Federated and distributed learning applications for electronic health records and structured medical data: A scoping review

Federated learning (FL) has gained popularity in clinical research in recent years to facilitate privacy-preserving collaboration. Structured data, one of the most prevalent forms of clinical data, has experienced significant growth in volume concurrently, notably with the widespread adoption of electronic health records in clinical practice. This review examines FL applications on structured medical data, identifies contemporary limitations and discusses potential innovations. We searched five databases, SCOPUS, MEDLINE, Web of Science, Embase, and CINAHL, to identify articles that applied FL to structured medical data and reported results following the PRISMA guidelines. Each selected publication was evaluated from three primary perspectives, including data quality, modeling strategies, and FL frameworks. Out of the 1160 papers screened, 34 met the inclusion criteria, with each article consisting of one or more studies that used FL to handle structured clinical/medical data. Of these, 24 utilized data acquired from electronic health records, with clinical predictions and association studies being the most common clinical research tasks that FL was applied to. Only one article exclusively explored the vertical FL setting, while the remaining 33 explored the horizontal FL setting, with only 14 discussing comparisons between single-site (local) and FL (global) analysis. The existing FL applications on structured medical data lack sufficient evaluations of clinically meaningful benefits, particularly when compared to single-site analyses. Therefore, it is crucial for future FL applications to prioritize clinical motivations and develop designs and methodologies that can effectively support and aid clinical practice and research.

cs.LG↗
arXiv2023

A roadmap to fair and trustworthy prediction model validation in healthcare

A prediction model is most useful if it generalizes beyond the development data with external validations, but to what extent should it generalize remains unclear. In practice, prediction models are externally validated using data from very different settings, including populations from other health systems or countries, with predictably poor results. This may not be a fair reflection of the performance of the model which was designed for a specific target population or setting, and may be stretching the expected model generalizability. To address this, we suggest to externally validate a model using new data from the target population to ensure clear implications of validation performance on model reliability, whereas model generalizability to broader settings should be carefully investigated during model development instead of explored post-hoc. Based on this perspective, we propose a roadmap that facilitates the development and application of reliable, fair, and trustworthy artificial intelligence prediction models.

cs.LG↗
arXiv2023

Epicasting: An Ensemble Wavelet Neural Network (EWNet) for Forecasting Epidemics

Infectious diseases remain among the top contributors to human illness and death worldwide, among which many diseases produce epidemic waves of infection. The unavailability of specific drugs and ready-to-use vaccines to prevent most of these epidemics makes the situation worse. These force public health officials and policymakers to rely on early warning systems generated by reliable and accurate forecasts of epidemics. Accurate forecasts of epidemics can assist stakeholders in tailoring countermeasures, such as vaccination campaigns, staff scheduling, and resource allocation, to the situation at hand, which could translate to reductions in the impact of a disease. Unfortunately, most of these past epidemics exhibit nonlinear and non-stationary characteristics due to their spreading fluctuations based on seasonal-dependent variability and the nature of these epidemics. We analyse a wide variety of epidemic time series datasets using a maximal overlap discrete wavelet transform (MODWT) based autoregressive neural network and call it EWNet model. MODWT techniques effectively characterize non-stationary behavior and seasonal dependencies in the epidemic time series and improve the nonlinear forecasting scheme of the autoregressive neural network in the proposed ensemble wavelet network framework. From a nonlinear time series viewpoint, we explore the asymptotic stationarity of the proposed EWNet model to show the asymptotic behavior of the associated Markov Chain. We also theoretically investigate the effect of learning stability and the choice of hidden neurons in the proposal. From a practical perspective, we compare our proposed EWNet framework with several statistical, machine learning, and deep learning models. Experimental results show that the proposed EWNet is highly competitive compared to the state-of-the-art epidemic forecasting methods.

cs.LG↗
arXiv2023

FedScore: A privacy-preserving framework for federated scoring system development

We propose FedScore, a privacy-preserving federated learning framework for scoring system generation across multiple sites to facilitate cross-institutional collaborations. The FedScore framework includes five modules: federated variable ranking, federated variable transformation, federated score derivation, federated model selection and federated model evaluation. To illustrate usage and assess FedScore's performance, we built a hypothetical global scoring system for mortality prediction within 30 days after a visit to an emergency department using 10 simulated sites divided from a tertiary hospital in Singapore. We employed a pre-existing score generator to construct 10 local scoring systems independently at each site and we also developed a scoring system using centralized data for comparison. We compared the acquired FedScore model's performance with that of other scoring models using the receiver operating characteristic (ROC) analysis. The FedScore model achieved an average area under the curve (AUC) value of 0.763 across all sites, with a standard deviation (SD) of 0.020. We also calculated the average AUC values and SDs for each local model, and the FedScore model showed promising accuracy and stability with a high average AUC value which was closest to the one of the pooled model and SD which was lower than that of most local models. This study demonstrates that FedScore is a privacy-preserving scoring system generator with potentially good generalizability.

cs.LG↗
arXiv2023

Resource Allocation for Cell-free Massive MIMO-enabled URLLC Downlink Systems

Ultra-reliable and low-latency communication (URLLC) is a pivotal technique for enabling the wireless control over industrial Internet-of-Things (IIoT) devices. By deploying distributed access points (APs), cell-free massive multiple-input and multiple-output (CF mMIMO) has great potential to provide URLLC services for IIoT devices. In this paper, we investigate CF mMIMO-enabled URLLC in a smart factory. Lower bounds (LBs) of downlink ergodic data rate under finite channel blocklength (FCBL) with imperfect channel state information (CSI) are derived for maximum-ratio transmission (MRT), full-pilot zero-forcing (FZF), and local zero-forcing (LZF) precoding schemes. Meanwhile, the weighted sum rate is maximized by jointly optimizing the pilot power and transmission power based on the derived LBs. Specifically, we first provide the globally optimal solution of the pilot power, and then introduce some approximations to transform the original problems into a series of subproblems, which can be expressed in a geometric programming (GP) form that can be readily solved. Finally, an iterative algorithm is proposed to optimize the power allocation based on various precoding schemes. Simulation results demonstrate that the proposed algorithm is superior to the existing algorithms, and that the quality of URLLC services will benefit by deploying more APs, except for the FZF precoding scheme.

cs.IT↗
arXiv2023

The Capacity Region of Distributed Multi-User Secret Sharing under The Perfect Privacy Condition

We study the distributed multi-user secret sharing (DMUSS) problem under the perfect privacy condition. In a DMUSS problem, multiple secret messages are deployed and the shares are offloaded to the storage nodes. Moreover, the access structure is extremely incomplete, as the decoding collection of each secret message has only one set, and by the perfect privacy condition such collection is also the colluding collection of all other secret messages. The secret message rate is defined as the size of the secret message normalized by the size of a share. We characterize the capacity region of the DMUSS problem when given an access structure, defined as the set of all achievable rate tuples. In the achievable scheme, we assume all shares are mutually independent and then design the decoding function based on the fact that the decoding collection of each secret message has only one set. Then it turns out that the perfect privacy condition is equivalent to the full rank property of some matrices consisting of different indeterminates and zeros. Such a solution does exist if the field size is bigger than the number of secret messages. Finally with a matching converse saying that the size of the secret is upper bounded by the sum of sizes of non-colluding shares, we characterize the capacity region of DMUSS problem under the perfect privacy condition.

cs.IT↗
arXiv2023

Discrete gradient structure of a second-order variable-step method for nonlinear integro-differential models

The discrete gradient structure and the positive definiteness of discrete fractional integrals or derivatives are fundamental to the numerical stability in long-time simulation of nonlinear integro-differential models. We build up a discrete gradient structure for a class of second-order variable-step approximations of fractional Riemann-Liouville integral and fractional Caputo derivative. Then certain variational energy dissipation laws at discrete levels of the corresponding variable-step Crank-Nicolson type methods are established for time-fractional Allen-Cahn and time-fractional Klein-Gordon type models. They are shown to be asymptotically compatible with the associated energy laws of the classical Allen-Cahn and Klein-Gordon equations in the associated fractional order limits.Numerical examples together with an adaptive time-stepping procedure are provided to demonstrate the effectiveness of our second-order methods.

math.NA↗
arXiv2023

Compositional Visual Generation with Composable Diffusion Models

Large text-guided diffusion models, such as DALLE-2, are able to generate stunning photorealistic images given natural language descriptions. While such models are highly flexible, they struggle to understand the composition of certain concepts, such as confusing the attributes of different objects or relations between objects. In this paper, we propose an alternative structured approach for compositional generation using diffusion models. An image is generated by composing a set of diffusion models, with each of them modeling a certain component of the image. To do this, we interpret diffusion models as energy-based models in which the data distributions defined by the energy functions may be explicitly combined. The proposed method can generate scenes at test time that are substantially more complex than those seen in training, composing sentence descriptions, object relations, human facial attributes, and even generalizing to new combinations that are rarely seen in the real world. We further illustrate how our approach may be used to compose pre-trained text-guided diffusion models and generate photorealistic images containing all the details described in the input descriptions, including the binding of certain object attributes that have been shown difficult for DALLE-2. These results point to the effectiveness of the proposed method in promoting structured generalization for visual generation. Project page: https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/

cs.CV↗
arXiv2023

A Framework for Mutual Information-based MIMO Integrated Sensing and Communication Beamforming Design

Integrated sensing and communication (ISAC) unifies sensing and communication, and improves the efficiency of the spectrum, energy, and hardware. In this work, we investigate the ISAC beamforming design to maximize the mutual information between the target response matrix of a point radar target and the echo signals, while ensuring the data rate requirements of the communication users. In order to study the impact of the echo interference caused by communication users on sensing performance, we study two scenarios: a single communication user and multiple communication users. For the case of a single communication user, we consider three types of echo interference, no interference, a point interference, and an extended interference. For the case of multiple communication users, the interference is also an extended one, and furthermore, each user's communication rate requirement needs to be satisfied. To find the optimal beamforming design in these problems, we provide a closed-form solution with low complexiy, a semidefinite relaxation (SDR) method, a low-complexity algorithm based on the Majorization-Minimization (MM) method and the successive convex approximation (SCA) method, and an algorithm based on MM method and SCA method, respectively. Numerical results demonstrate that, compared to the ISAC beamforming schemes based on the Cramér-Rao bound (CRB) metric and the beampattern metric, the proposed mutual information metric can bring better beampattern and root mean square error (RMSE) of angle estimation. Furthermore, our proposed schemes designed based on the mutual information metric can suppress the echo interference from the communication users effectively.

eess.SP↗
arXiv2022

An ensemble neural network approach to forecast Dengue outbreak based on climatic condition

Dengue fever is a virulent disease spreading over 100 tropical and subtropical countries in Africa, the Americas, and Asia. This arboviral disease affects around 400 million people globally, severely distressing the healthcare systems. The unavailability of a specific drug and ready-to-use vaccine makes the situation worse. Hence, policymakers must rely on early warning systems to control intervention-related decisions. Forecasts routinely provide critical information for dangerous epidemic events. However, the available forecasting models (e.g., weather-driven mechanistic, statistical time series, and machine learning models) lack a clear understanding of different components to improve prediction accuracy and often provide unstable and unreliable forecasts. This study proposes an ensemble wavelet neural network with exogenous factor(s) (XEWNet) model that can produce reliable estimates for dengue outbreak prediction for three geographical regions, namely San Juan, Iquitos, and Ahmedabad. The proposed XEWNet model is flexible and can easily incorporate exogenous climate variable(s) confirmed by statistical causality tests in its scalable framework. The proposed model is an integrated approach that uses wavelet transformation into an ensemble neural network framework that helps in generating more reliable long-term forecasts. The proposed XEWNet allows complex non-linear relationships between the dengue incidence cases and rainfall; however, mathematically interpretable, fast in execution, and easily comprehensible. The proposal's competitiveness is measured using computational experiments based on various statistical metrics and several statistical comparison tests. In comparison with statistical, machine learning, and deep learning methods, our proposed XEWNet performs better in 75% of the cases for short-term and long-term forecasting of dengue incidence.

q-bio.PE↗
arXiv2022

Shapley variable importance cloud for machine learning models

Current practice in interpretable machine learning often focuses on explaining the final model trained from data, e.g., by using the Shapley additive explanations (SHAP) method. The recently developed Shapley variable importance cloud (ShapleyVIC) extends the current practice to a group of "nearly optimal models" to provide comprehensive and robust variable importance assessments, with estimated uncertainty intervals for a more complete understanding of variable contributions to predictions. ShapleyVIC was initially developed for applications with traditional regression models, and the benefits of ShapleyVIC inference have been demonstrated in real-life prediction tasks using the logistic regression model. However, as a model-agnostic approach, ShapleyVIC application is not limited to such scenarios. In this work, we extend ShapleyVIC implementation for machine learning models to enable wider applications, and propose it as a useful complement to the current SHAP analysis to enable more trustworthy applications of these black-box models.

cs.LG↗
arXiv2022

On the Asymptotic Capacity of Information Theoretical Privacy-preserving Epidemiological Data Collection

We formulate a new secure distributed computation problem, where a simulation center can require any linear combination of $ K $ users' data through a caching layer consisting of $ N $ servers. The users, servers, and data collector do not trust each other. For users, any data is required to be protected from up to $ E $ servers; for servers, any more information than the desired linear combination cannot be leaked to the data collector; and for the data collector, any single server knows nothing about the coefficients of the linear combination. Our goal is to find the optimal download cost, which is defined as the size of message uploaded to the simulation center by the servers, to the size of desired linear combination. We proposed a scheme with the optimal download cost when $E < N-1$. We also prove that when $E\geq N-1$, the scheme is not feasible.

cs.IT↗
arXiv2022

Resource Allocation for Uplink Cell-Free Massive MIMO enabled URLLC in a Smart Factory

Smart factories need to support the simultaneous communication of multiple industrial Internet-of-Things (IIoT) devices with ultra-reliability and low-latency communication (URLLC). Meanwhile, short packet transmission for IIoT applications incurs performance loss compared to traditional long packet transmission for human-to-human communications. On the other hand, cell-free massive multiple-input and multiple-output (CF mMIMO) technology can provide uniform services for all devices by deploying distributed access points (APs). In this paper, we adopt CF mMIMO to support URLLC in a smart factory. Specifically, we first derive the lower bound (LB) on achievable uplink data rate under the finite blocklength (FBL) with imperfect channel state information (CSI) for both maximum-ratio combining (MRC) and full-pilot zero-forcing (FZF) decoders. \textcolor{black}{The derived LB rates based on the MRC case have the same trends as the ergodic rate, while LB rates using the FZF decoder tightly match the ergodic rates}, which means that resource allocation can be performed based on the LB data rate rather the exact ergodic data rate under FBL. The \textcolor{black}{log-function method} and successive convex approximation (SCA) are then used to approximately transform the non-convex weighted sum rate problem into a series of geometric program (GP) problems, and an iterative algorithm is proposed to jointly optimize the pilot and payload power allocation. Simulation results demonstrate that CF mMIMO significantly improves the average weighted sum rate (AWSR) compared to centralized mMIMO. An interesting observation is that increasing the number of devices improves the AWSR for CF mMIMO whilst the AWSR remains relatively constant for centralized mMIMO.

cs.IT↗
arXiv2022

Integrated Sensing and Communication Beamforming Design Based on Mutual Information

Integrated sensing and communication (ISAC) unifies radar sensing and communication, and improves the efficiency of the spectrum, energy and hardware. In this paper, we investigate the ISAC beamforming design in a downlink system with a communication user and a point radar target to be perceived. The design criterion for radar sensing is the mutual information between the target response matrix and the echo signals, while the single user transmission rate is used as the performance metric of the communication. Two scenarios without and with interference from the communication user are investigated. A closed-form solution with low complexity and a solution based on the semidefinite relaxation (SDR) method are provided to solve these two problems, respectively. Numerical results demonstrate that, compared to the results obtained by SDR based on the CVX toolbox, the closed-form solution is tight in the feasible region. In addition, we show that the SDR method obtains an optimal solution.

eess.SP↗
arXiv2022

Asymptotically compatible energy of variable-step fractional BDF2 formula for time-fractional Cahn-Hilliard model

A new discrete energy dissipation law of the variable-step fractional BDF2 (second-order backward differentiation formula) scheme is established for time-fractional Cahn-Hilliard model with the Caputo's fractional derivative of order $α\in(0,1)$, under a weak step-ratio constraint $0.4753\le τ_k/τ_{k-1}<r^*(α)$, where $τ_k$ is the $k$-th time-step size and $r^*(α)\ge4.660$ for $α\in(0,1)$.We propose a novel discrete gradient structure by a local-nonlocal splitting technique, that is, the fractional BDF2 formula is split into a local part analogue to the two-step backward differentiation formula of the first derivative and a nonlocal part analogue to the L1-type formula of the Caputo's derivative. More interestingly, in the sense of the limit $α\rightarrow1^-$, the discrete energy and the corresponding energy dissipation law are asymptotically compatible with the associated discrete energy and the energy dissipation law of the variable-step BDF2 method for the classical Cahn-Hilliard equation, respectively. Numerical examples with an adaptive stepping procedure are provided to demonstrate the accuracy and the effectiveness of our proposed method.

math.NA↗
arXiv2022

Handling missing values in healthcare data: A systematic review of deep learning-based imputation techniques

Objective: The proper handling of missing values is critical to delivering reliable estimates and decisions, especially in high-stakes fields such as clinical research. The increasing diversity and complexity of data have led many researchers to develop deep learning (DL)-based imputation techniques. We conducted a systematic review to evaluate the use of these techniques, with a particular focus on data types, aiming to assist healthcare researchers from various disciplines in dealing with missing values. Methods: We searched five databases (MEDLINE, Web of Science, Embase, CINAHL, and Scopus) for articles published prior to August 2021 that applied DL-based models to imputation. We assessed selected publications from four perspectives: health data types, model backbone (i.e., main architecture), imputation strategies, and comparison with non-DL-based methods. Based on data types, we created an evidence map to illustrate the adoption of DL models. Results: We included 64 articles, of which tabular static (26.6%, 17/64) and temporal data (37.5%, 24/64) were the most frequently investigated. We found that model backbone(s) differed among data types as well as the imputation strategy. The "integrated" strategy, that is, the imputation task being solved concurrently with downstream tasks, was popular for tabular temporal (50%, 12/24) and multi-modal data (71.4%, 5/7), but limited for other data types. Moreover, DL-based imputation methods yielded better imputation accuracy in most studies, compared with non-DL-based methods. Conclusion: DL-based imputation models can be customized based on data type, addressing the corresponding missing patterns, and its associated "integrated" strategy can enhance the efficacy of imputation, especially in scenarios where data is complex. Future research may focus on the portability and fairness of DL-based models for healthcare data imputation.

cs.LG↗