arXiv subjects

Huiyuan Yang

Publications and source records attributed to Huiyuan Yang.

At least 19 recordsLinked to original sources

arXiv2026

You Only Need One Stage: Novel-View Synthesis From A Single Blind Face Image

We propose a novel one-stage method, NVB-Face, for generating consistent Novel-View images directly from a single Blind Face image. Existing approaches to novel-view synthesis for objects or faces typically require a high-resolution RGB image as input. When dealing with degraded images, the conventional pipeline follows a two-stage process: first restoring the image to high resolution, then synthesizing novel views from the restored result. However, this approach is highly dependent on the quality of the restored image, often leading to inaccuracies and inconsistencies in the final output. To address this limitation, we extract single-view features directly from the blind face image and introduce a feature manipulator that transforms these features into 3D-aware, multi-view latent representations. Leveraging the powerful generative capacity of a diffusion model, our framework synthesizes high-quality, consistent novel-view face images. Experimental results show that our method significantly outperforms traditional two-stage approaches in both consistency and fidelity.

cs.CV↗

arXiv2025

LEAVES: Learning Views for Time-Series Biobehavioral Data in Contrastive Learning

Contrastive learning has been utilized as a promising self-supervised learning approach to extract meaningful representations from unlabeled data. The majority of these methods take advantage of data-augmentation techniques to create diverse views from the original input. However, optimizing augmentations and their parameters for generating more effective views in contrastive learning frameworks is often resource-intensive and time-consuming. While several strategies have been proposed for automatically generating new views in computer vision, research in other domains, such as time-series biobehavioral data, remains limited. In this paper, we introduce a simple yet powerful module for automatic view generation in contrastive learning frameworks applied to time-series biobehavioral data, which is essential for modern health care, termed learning views for time-series data (LEAVES). This proposed module employs adversarial training to learn augmentation hyperparameters within contrastive learning frameworks. We assess the efficacy of our method on multiple time-series datasets using two well-known contrastive learning frameworks, namely SimCLR and BYOL. Across four diverse biobehavioral datasets, LEAVES requires only approximately 20 learnable parameters -- dramatically fewer than the about 580k parameters demanded by frameworks like ViewMaker, a previously proposed adversarially trained convolutional module in contrastive learning, while achieving competitive and often superior performance to existing baseline methods. Crucially, these efficiency gains are obtained without extensive manual hyperparameter tuning, which makes LEAVES particularly suitable for large-scale or real-time healthcare applications that demand both accuracy and practicality.

cs.LG↗

arXiv2025

Scoring ISAC: Benchmarking Integrated Sensing and Communications via Score-Based Generative Modeling

Integrated sensing and communications (ISAC) is a key enabler for next-generation wireless systems, aiming to support both high-throughput communication and high-accuracy environmental sensing using shared spectrum and hardware. Theoretical performance metrics, such as mutual information (MI), minimum mean squared error (MMSE), and Bayesian Cramér--Rao bound (BCRB), play a key role in evaluating ISAC system performance limits. However, in practice, hardware impairments, multipath propagation, interference, and scene constraints often result in nonlinear, multimodal, and non-Gaussian distributions, making it challenging to derive these metrics analytically. Recently, there has been a growing interest in applying score-based generative models to characterize these metrics from data, although not discussed for ISAC. This paper provides a tutorial-style summary of recent advances in score-based performance evaluation, with a focus on ISAC systems. We refer to the summarized framework as scoring ISAC, which not only reflects the core methodology based on score functions but also emphasizes the goal of scoring (i.e., evaluating) ISAC systems under realistic conditions. We present the connections between classical performance metrics and the score functions and provide the practical training techniques for learning score functions to estimate performance metrics. Proof-of-concept experiments on target detection and localization validate the accuracy of score-based performance estimators against ground-truth analytical expressions, illustrating their ability to replicate and extend traditional analyses in more complex, realistic settings. This framework demonstrates the great potential of score-based generative models in ISAC performance analysis, algorithm design, and system optimization.

eess.SP↗

arXiv2024

Indirect Lossy Source Coding with Observed Source Reconstruction: Nonasymptotic Bounds and Second-Order Asymptotics

This paper considers the joint compression of a pair of correlated sources, where the encoder is allowed to access only one of the sources. The objective is to recover both sources under separate distortion constraints for each source while minimizing the rate. This problem generalizes the indirect lossy source coding problem by also requiring the recovery of the observed source. In this paper, we aim to study the nonasymptotic and second-order asymptotic properties of this problem. Specifically, we begin by deriving nonasymptotic achievability and converse bounds valid for general sources and distortion measures. The source dispersion (Gaussian approximation) is then determined through asymptotic analysis of the nonasymptotic bounds. We further examine the case of erased fair coin flips (EFCF) and provide its specific nonasymptotic achievability and converse bounds. Numerical results under the EFCF case demonstrate that our second-order asymptotic approximation closely approximates the optimum rate at appropriately large blocklengths.

cs.IT↗

arXiv2024

On the Second-Order Achievabilities of Indirect Quadratic Lossy Source Coding

This paper studies the second-order achievabilities of indirect quadratic lossy source coding for a specific class of source models, where the term "quadratic" denotes that the reconstruction fidelity of the hidden source is quantified by a squared error distortion measure. Specifically, it is assumed that the hidden source $S$ can be expressed as $S = φ(X) + W$, where $X$ is the observable source with alphabet $\mathcal{X}$, $φ(\cdot)$ is a deterministic function, and $W$ is a random variable independent of $X$, satisfying $\mathbb{E}[W] = 0$, $\mathbb{E}[W^2] > 0$, $\mathbb{E}[W^3] = 0$, and $\mathbb{E}[W^6] < \infty$. Additionally, both the set $\{φ(x):\ x \in \mathcal{X} \}$ and the reconstruction alphabet for $S$ are assumed to be bounded. Under the above settings, a second-order achievability bound is established using techniques based on distortion-tilted information. This result is then generalized to the case of indirect quadratic lossy source coding with observed source reconstruction, where reconstruction is required for both the hidden source $S$ and the observable source $X$, and the distortion measure for $X$ is not necessarily quadratic. These obtained bounds are consistent in form with their finite-alphabet counterparts, which have been proven to be second-order tight.

cs.IT↗

arXiv2024

UAV-Enabled Asynchronous Federated Learning

To exploit unprecedented data generation in mobile edge networks, federated learning (FL) has emerged as a promising alternative to the conventional centralized machine learning (ML). However, there are some critical challenges for FL deployment. One major challenge called straggler issue severely limits FL's coverage where the device with the weakest channel condition becomes the bottleneck of the model aggregation performance. Besides, the huge uplink communication overhead compromises the effectiveness of FL, which is particularly pronounced in large-scale systems. To address the straggler issue, we propose the integration of an unmanned aerial vehicle (UAV) as the parameter server (UAV-PS) to coordinate the FL implementation. We further employ over-the-air computation technique that leverages the superposition property of wireless channels for efficient uplink communication. Specifically, in this paper, we develop a novel UAV-enabled over-the-air asynchronous FL (UAV-AFL) framework which supports the UAV-PS in updating the model continuously to enhance the learning performance. Moreover, we conduct a convergence analysis to quantitatively capture the impact of model asynchrony, device selection and communication errors on the UAV-AFL learning performance. Based on this, a unified communication-learning problem is formulated to maximize asymptotical learning performance by optimizing the UAV-PS trajectory, device selection and over-the-air transceiver design. Simulation results demonstrate that the proposed scheme achieves substantially learning efficiency improvement compared with the state-of-the-art approaches.

eess.SP↗

arXiv2024

Joint Data and Semantics Lossy Compression: Nonasymptotic Converse Bounds and Second-Order Asymptotics

This paper studies the joint data and semantics lossy compression problem, i.e., an extension of the hidden lossy source coding problem that entails recovering both the hidden and observable sources. We aim to study the nonasymptotic and second-order properties of this problem, especially the converse aspect. Specifically, we begin by deriving general nonasymptotic converse bounds valid for general sources and distortion measures, utilizing properties of distortion-tilted information. Subsequently, a second-order converse bound is derived under the standard block coding setting through asymptotic analysis of the nonasymptotic bounds. This bound is tight since it coincides with a known second-order achievability bound. We then examine the case of erased fair coin flips (EFCF), providing its specific nonasymptotic achievability and converse bounds. Numerical results under the EFCF case demonstrate that our second-order asymptotic approximation effectively approximates the optimum rate at given blocklengths.

cs.IT↗

arXiv2023

Integrating Communication, Sensing and Computing in Satellite Internet of Things: Challenges and Opportunities

Satellite Internet of Things (IoT) is to use satellites as the access points for IoT devices to achieve the global coverage of future IoT systems, and is expected to support burgeoning IoT applications, including communication, sensing, and computing. However, the complex and dynamic satellite environments and limited network resources raise new challenges in the design of satellite IoT systems. In this article, we focus on the joint design of communication, sensing, and computing to improve the performance of satellite IoT, which is quite different from the case of terrestrial IoT systems. We describe how the integration of the three functions can enhance system capabilities, and summarize the state-of-the-art solutions. Furthermore, we discuss the main challenges of integrating communication, sensing, and computing in satellite IoT to be solved with pressing interest.

eess.SP↗

arXiv2023

ECG-SL: Electrocardiogram(ECG) Segment Learning, a deep learning method for ECG signal

Electrocardiogram (ECG) is an essential signal in monitoring human heart activities. Researchers have achieved promising results in leveraging ECGs in clinical applications with deep learning models. However, the mainstream deep learning approaches usually neglect the periodic and formative attribute of the ECG heartbeat waveform. In this work, we propose a novel ECG-Segment based Learning (ECG-SL) framework to explicitly model the periodic nature of ECG signals. More specifically, ECG signals are first split into heartbeat segments, and then structural features are extracted from each of the segments. Based on the structural features, a temporal model is designed to learn the temporal information for various clinical tasks. Further, due to the fact that massive ECG signals are available but the labeled data are very limited, we also explore self-supervised learning strategy to pre-train the models, resulting significant improvement for downstream tasks. The proposed method outperforms the baseline model and shows competitive performances compared with task-specific methods in three clinical applications: cardiac condition diagnosis, sleep apnea detection, and arrhythmia classification. Further, we find that the ECG-SL tends to focus more on each heartbeat's peak and ST range than ResNet by visualizing the saliency maps.

cs.LG↗

arXiv2023

Empirical Study of Mix-based Data Augmentation Methods in Physiological Time Series Data

Data augmentation is a common practice to help generalization in the procedure of deep model training. In the context of physiological time series classification, previous research has primarily focused on label-invariant data augmentation methods. However, another class of augmentation techniques (\textit{i.e., Mixup}) that emerged in the computer vision field has yet to be fully explored in the time series domain. In this study, we systematically review the mix-based augmentations, including mixup, cutmix, and manifold mixup, on six physiological datasets, evaluating their performance across different sensory data and classification tasks. Our results demonstrate that the three mix-based augmentations can consistently improve the performance on the six datasets. More importantly, the improvement does not rely on expert knowledge or extensive parameter tuning. Lastly, we provide an overview of the unique properties of the mix-based augmentation methods and highlight the potential benefits of using the mix-based augmentation in physiological time series data.

cs.LG↗

arXiv2023

Weakly-Supervised Text-driven Contrastive Learning for Facial Behavior Understanding

Contrastive learning has shown promising potential for learning robust representations by utilizing unlabeled data. However, constructing effective positive-negative pairs for contrastive learning on facial behavior datasets remains challenging. This is because such pairs inevitably encode the subject-ID information, and the randomly constructed pairs may push similar facial images away due to the limited number of subjects in facial behavior datasets. To address this issue, we propose to utilize activity descriptions, coarse-grained information provided in some datasets, which can provide high-level semantic information about the image sequences but is often neglected in previous studies. More specifically, we introduce a two-stage Contrastive Learning with Text-Embeded framework for Facial behavior understanding (CLEF). The first stage is a weakly-supervised contrastive learning method that learns representations from positive-negative pairs constructed using coarse-grained activity information. The second stage aims to train the recognition of facial expressions or facial action units by maximizing the similarity between image and the corresponding text label names. The proposed CLEF achieves state-of-the-art performance on three in-the-lab datasets for AU recognition and three in-the-wild datasets for facial expression recognition.

cs.CV↗

arXiv2023

Multimodal Channel-Mixing: Channel and Spatial Masked AutoEncoder on Facial Action Unit Detection

Recent studies have focused on utilizing multi-modal data to develop robust models for facial Action Unit (AU) detection. However, the heterogeneity of multi-modal data poses challenges in learning effective representations. One such challenge is extracting relevant features from multiple modalities using a single feature extractor. Moreover, previous studies have not fully explored the potential of multi-modal fusion strategies. In contrast to the extensive work on late fusion, there are limited investigations on early fusion for channel information exploration. This paper presents a novel multi-modal reconstruction network, named Multimodal Channel-Mixing (MCM), as a pre-trained model to learn robust representation for facilitating multi-modal fusion. The approach follows an early fusion setup, integrating a Channel-Mixing module, where two out of five channels are randomly dropped. The dropped channels then are reconstructed from the remaining channels using masked autoencoder. This module not only reduces channel redundancy, but also facilitates multi-modal learning and reconstruction capabilities, resulting in robust feature learning. The encoder is fine-tuned on a downstream task of automatic facial action unit detection. Pre-training experiments were conducted on BP4D+, followed by fine-tuning on BP4D and DISFA to assess the effectiveness and robustness of the proposed framework. The results demonstrate that our method meets and surpasses the performance of state-of-the-art baseline methods.

cs.CV↗

arXiv2023

PiRL: Participant-Invariant Representation Learning for Healthcare Using Maximum Mean Discrepancy and Triplet Loss

Due to individual heterogeneity, person-specific models are usually achieving better performance than generic (one-size-fits-all) models in data-driven health applications. However, generic models are usually preferable in real-world applications, due to the difficulties of developing person-specific models, such as new-user-adaptation issues and system complexities. To improve the performance of generic models, we propose a Participant-invariant Representation Learning (PiRL) framework, which utilizes maximum mean discrepancy (MMD) loss and domain-adversarial training to encourage the model to learn participant-invariant representations. Further, to avoid trivial solutions in the learned representations, a triplet loss based constraint is used for the model to learn the label-distinguishable embeddings. The proposed framework is evaluated on two public datasets (CLAS and Apnea-ECG), and significant performance improvements are achieved compared to the baseline models.

eess.SP↗

arXiv2023

Federated Learning with Lossy Distributed Source Coding: Analysis and Optimization

Recently, federated learning (FL), which replaces data sharing with model sharing, has emerged as an efficient and privacy-friendly machine learning (ML) paradigm. One of the main challenges in FL is the huge communication cost for model aggregation. Many compression/quantization schemes have been proposed to reduce the communication cost for model aggregation. However, the following question remains unanswered: What is the fundamental trade-off between the communication cost and the FL convergence performance? In this paper, we manage to answer this question. Specifically, we first put forth a general framework for model aggregation performance analysis based on the rate-distortion theory. Under the proposed analysis framework, we derive an inner bound of the rate-distortion region of model aggregation. We then conduct an FL convergence analysis to connect the aggregation distortion and the FL convergence performance. We formulate an aggregation distortion minimization problem to improve the FL convergence performance. Two algorithms are developed to solve the above problem. Numerical results on aggregation distortion, convergence performance, and communication cost demonstrate that the baseline model aggregation schemes still have great potential for further improvement.

eess.SP↗

arXiv2022

PiRL: Participant-Invariant Representation Learning for Healthcare

Due to individual heterogeneity, performance gaps are observed between generic (one-size-fits-all) models and person-specific models in data-driven health applications. However, in real-world applications, generic models are usually more favorable due to new-user-adaptation issues and system complexities, etc. To improve the performance of the generic model, we propose a representation learning framework that learns participant-invariant representations, named PiRL. The proposed framework utilizes maximum mean discrepancy (MMD) loss and domain-adversarial training to encourage the model to learn participant-invariant representations. Further, a triplet loss, which constrains the model for inter-class alignment of the representations, is utilized to optimize the learned representations for downstream health applications. We evaluated our frameworks on two public datasets related to physical and mental health, for detecting sleep apnea and stress, respectively. As preliminary results, we found the proposed approach shows around a 5% increase in accuracy compared to the baseline.

cs.LG↗

arXiv2022

Empirical Evaluation of Data Augmentations for Biobehavioral Time Series Data with Deep Learning

Deep learning has performed remarkably well on many tasks recently. However, the superior performance of deep models relies heavily on the availability of a large number of training data, which limits the wide adaptation of deep models on various clinical and affective computing tasks, as the labeled data are usually very limited. As an effective technique to increase the data variability and thus train deep models with better generalization, data augmentation (DA) is a critical step for the success of deep learning models on biobehavioral time series data. However, the effectiveness of various DAs for different datasets with different tasks and deep models is understudied for biobehavioral time series data. In this paper, we first systematically review eight basic DA methods for biobehavioral time series data, and evaluate the effects on seven datasets with three backbones. Next, we explore adapting more recent DA techniques (i.e., automatic augmentation, random augmentation) to biobehavioral time series data by designing a new policy architecture applicable to time series data. Last, we try to answer the question of why a DA is effective (or not) by first summarizing two desired attributes for augmentations (challenging and faithful), and then utilizing two metrics to quantitatively measure the corresponding attributes, which can guide us in the search for more effective DA for biobehavioral time series data by designing more challenging but still faithful transformations. Our code and results are available at Link.

cs.LG↗

arXiv2022

UAV-Assisted Hierarchical Aggregation for Over-the-Air Federated Learning

With huge amounts of data explosively increasing in the mobile edge, over-the-air federated learning (OA-FL) emerges as a promising technique to reduce communication costs and privacy leak risks. However, when devices in a relatively large area cooperatively train a machine learning model, the attendant straggler issues will significantly reduce the learning performance. In this paper, we propose an unmanned aerial vehicle (UAV) assisted OA-FL system, where the UAV acts as a parameter server (PS) to aggregate the local gradients hierarchically for global model updating. Under this UAV-assisted hierarchical aggregation scheme, we carry out a gradient-correlation-aware FL performance analysis. We then formulate a mean squared error (MSE) minimization problem to tune the UAV trajectory and the global aggregation coefficients based on the analysis results. An algorithm based on alternating optimization (AO) and successive convex approximation (SCA) is developed to solve the formulated problem. Simulation results demonstrate the great potential of our UAV-assisted hierarchical aggregation scheme.

eess.SP↗

arXiv2022

Over-the-Air Federated Multi-Task Learning Over MIMO Multiple Access Channels

With the explosive growth of data and wireless devices, federated learning (FL) over wireless medium has emerged as a promising technology for large-scale distributed intelligent systems. Yet, the urgent demand for ubiquitous intelligence will generate a large number of concurrent FL tasks, which may seriously aggravate the scarcity of communication resources. By exploiting the analog superposition of electromagnetic waves, over-the-air computation (AirComp) is an appealing solution to alleviate the burden of communication required by FL. However, sharing frequency-time resources in over-the-air computation inevitably brings about the problem of inter-task interference, which poses a new challenge that needs to be appropriately addressed. In this paper, we study over-the-air federated multi-task learning (OA-FMTL) over the multiple-input multiple-output (MIMO) multiple access (MAC) channel. We propose a novel model aggregation method for the alignment of local gradients of different devices, which alleviates the straggler problem in over-the-air computation due to the channel heterogeneity. We establish a communication-learning analysis framework for the proposed OA-FMTL scheme by considering the spatial correlation between devices, and formulate an optimization problem for the design of transceiver beamforming and device selection. To solve this problem, we develop an algorithm by using alternating optimization (AO) and fractional programming (FP), which effectively mitigates the impact of inter-task interference on the FL learning performance. We show that due to the use of the new model aggregation method, device selection is no longer essential, thereby avoiding the heavy computational burden involved in selecting active devices. Numerical results demonstrate the validity of the analysis and the superb performance of the proposed scheme.

eess.SP↗