Searcharxiv⌕ Search

arXiv subjects

Jian Wang

Publications and source records attributed to Jian Wang.

At least 559 records · Page 31Linked to original sources
arXiv2023

PBScaler: A Bottleneck-aware Autoscaling Framework for Microservice-based Applications

Autoscaling is critical for ensuring optimal performance and resource utilization in cloud applications with dynamic workloads. However, traditional autoscaling technologies are typically no longer applicable in microservice-based applications due to the diverse workload patterns and complex interactions between microservices. Specifically, the propagation of performance anomalies through interactions leads to a high number of abnormal microservices, making it difficult to identify the root performance bottlenecks (PBs) and formulate appropriate scaling strategies. In addition, to balance resource consumption and performance, the existing mainstream approaches based on online optimization algorithms require multiple iterations, leading to oscillation and elevating the likelihood of performance degradation. To tackle these issues, we propose PBScaler, a bottleneck-aware autoscaling framework designed to prevent performance degradation in a microservice-based application. The key insight of PBScaler is to locate the PBs. Thus, we propose TopoRank, a novel random walk algorithm based on the topological potential to reduce unnecessary scaling. By integrating TopoRank with an offline performance-aware optimization algorithm, PBScaler optimizes replica management without disrupting the online application. Comprehensive experiments demonstrate that PBScaler outperforms existing state-of-the-art approaches in mitigating performance issues while conserving resources efficiently.

cs.SE↗
arXiv2023

BARGAIN-MATCH: A Game Theoretical Approach for Resource Allocation and Task Offloading in Vehicular Edge Computing Networks

Vehicular edge computing (VEC) is emerging as a promising architecture of vehicular networks (VNs) by deploying the cloud computing resources at the edge of the VNs. This work aims to optimize resource allocation and task offloading in VEC networks. Specifically, we formulate a game theoretical resource allocation and task offloading problem (GTRATOP) that aims to maximize the system performance by jointly considering the incentive for cooperation, competition among vehicles, heterogeneity between VEC servers and vehicles, and inherent dynamic of VNs. Since the formulated GTRATOP is NP-hard, we propose an adaptive approach for resource allocation and task offloading in VEC networks by incorporating bargaining game and matching game, which is called BARGAIN-MATCH. First, for resource allocation, a bargaining game-based incentive is proposed to stimulate the vehicles and VEC servers to negotiate the optimal resource allocation and pricing decisions. Second, for task offloading, a many-to-one matching scheme is proposed to decide the optimal offloading strategies. Third, the dynamic and time-varying features are considered to adapt the strategies of BARGAIN-MATCH to the real-time VEC networks. Moreover, the BARGAIN-MATCH is proved to be stable and weak Pareto optimal. Simulation results demonstrate that the proposed BARGAIN-MATCH achieves superior system performance and efficiency compared to other methods, especially when the system workload is heavy.

cs.GT↗
arXiv2023

COOPER: Coordinating Specialized Agents towards a Complex Dialogue Goal

In recent years, there has been a growing interest in exploring dialogues with more complex goals, such as negotiation, persuasion, and emotional support, which go beyond traditional service-focused dialogue systems. Apart from the requirement for much more sophisticated strategic reasoning and communication skills, a significant challenge of these tasks lies in the difficulty of objectively measuring the achievement of their goals in a quantifiable way, making it difficult for existing research to directly optimize the dialogue procedure towards them. In our work, we emphasize the multifaceted nature of complex dialogue goals and argue that it is more feasible to accomplish them by comprehensively considering and jointly promoting their different aspects. To this end, we propose a novel dialogue framework, Cooper, which coordinates multiple specialized agents, each dedicated to a specific dialogue goal aspect separately, to approach the complex objective. Through this divide-and-conquer manner, we make complex dialogue goals more approachable and elicit greater intelligence via the collaboration of individual agents. Experiments on persuasion and emotional support dialogues demonstrate the superiority of our method over a set of competitive baselines.

cs.CL↗
arXiv2023

Taiyi: A Bilingual Fine-Tuned Large Language Model for Diverse Biomedical Tasks

Objective: Most existing fine-tuned biomedical large language models (LLMs) focus on enhancing performance in monolingual biomedical question answering and conversation tasks. To investigate the effectiveness of the fine-tuned LLMs on diverse biomedical NLP tasks in different languages, We present Taiyi, a bilingual fine-tuned LLM for diverse biomedical tasks. Materials and Methods: We first curated a comprehensive collection of 140 existing biomedical text mining datasets (102 English and 38 Chinese datasets) across over 10 task types. Subsequently, a two-stage strategy is proposed for supervised fine-tuning to optimize the model performance across varied tasks. Results: Experimental results on 13 test sets covering named entity recognition, relation extraction, text classification, question answering tasks demonstrate that Taiyi achieves superior performance compared to general LLMs. The case study involving additional biomedical NLP tasks further shows Taiyi's considerable potential for bilingual biomedical multi-tasking. Conclusion: Leveraging rich high-quality biomedical corpora and developing effective fine-tuning strategies can significantly improve the performance of LLMs within the biomedical domain. Taiyi shows the bilingual multi-tasking capability through supervised fine-tuning. However, those tasks such as information extraction that are not generation tasks in nature remain challenging for LLM-based generative approaches, and they still underperform the conventional discriminative approaches of smaller language models.

cs.CL↗
arXiv2023

Robust Communicative Multi-Agent Reinforcement Learning with Active Defense

Communication in multi-agent reinforcement learning (MARL) has been proven to effectively promote cooperation among agents recently. Since communication in real-world scenarios is vulnerable to noises and adversarial attacks, it is crucial to develop robust communicative MARL technique. However, existing research in this domain has predominantly focused on passive defense strategies, where agents receive all messages equally, making it hard to balance performance and robustness. We propose an active defense strategy, where agents automatically reduce the impact of potentially harmful messages on the final decision. There are two challenges to implement this strategy, that are defining unreliable messages and adjusting the unreliable messages' impact on the final decision properly. To address them, we design an Active Defense Multi-Agent Communication framework (ADMAC), which estimates the reliability of received messages and adjusts their impact on the final decision accordingly with the help of a decomposable decision structure. The superiority of ADMAC over existing methods is validated by experiments in three communication-critical tasks under four types of attacks.

cs.MA↗
arXiv2023

Quantum phase transitions in two-dimensional superconductors: a review on recent experimental progress

Superconductor-insulator/metal transition (SIT/SMT) as a paradigm of quantum phase transition has been a research highlight over the last three decades. Benefit from recent developments in the fabrication and measurements of 2D superconducting films and nanodevices, unprecedented quantum phenomena have been revealed in the quantum phase transitions of 2D superconductors. In this review, we introduce the recent progress on quantum phase transitions in 2D superconductors, focusing on the quantum Griffiths singularity (QGS) and anomalous metal state. Characterized by a divergent critical exponent when approaching zero temperature, QGS of SMT is discovered in ultrathin crystalline Ga films and subsequently detected in various 2D superconductors. The universality of QGS indicates the profound influence of quenched disorder on quantum phase transitions. Besides, in a 2D superconducting system, whether a metallic ground state can exist is a long-sought mystery. Recently, the charge-2e quantum oscillations are observed in nanopatterned superconducting films, indicating the bosonic nature of the anomalous metal state and ending the debate on whether bosons can exist as a metal. The evidences of the anomalous metal states have also been reported in crystalline epitaxial thin films and exfoliated nanoflakes, as well as granular composite films. High quality filters are used in these works to exclude the influence of external high frequency noises in ultralow temperature measurements. The observations of QGS and metallic ground states in 2D superconductors not only reveal the prominent role of quantum fluctuations and dissipations but also provide new perspective to explore quantum phase transitions in superconducting systems.

cond-mat.supr-con↗
arXiv2023

DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs

Close-up facial images captured at short distances often suffer from perspective distortion, resulting in exaggerated facial features and unnatural/unattractive appearances. We propose a simple yet effective method for correcting perspective distortions in a single close-up face. We first perform GAN inversion using a perspective-distorted input facial image by jointly optimizing the camera intrinsic/extrinsic parameters and face latent code. To address the ambiguity of joint optimization, we develop starting from a short distance, optimization scheduling, reparametrizations, and geometric regularization. Re-rendering the portrait at a proper focal length and camera distance effectively corrects perspective distortions and produces more natural-looking results. Our experiments show that our method compares favorably against previous approaches qualitatively and quantitatively. We showcase numerous examples validating the applicability of our method on in-the-wild portrait photos. We will release our code and the evaluation protocol to facilitate future work.

cs.CV↗
arXiv2023

Towards 4D Human Video Stylization

We present a first step towards 4D (3D and time) human video stylization, which addresses style transfer, novel view synthesis and human animation within a unified framework. While numerous video stylization methods have been developed, they are often restricted to rendering images in specific viewpoints of the input video, lacking the capability to generalize to novel views and novel poses in dynamic scenes. To overcome these limitations, we leverage Neural Radiance Fields (NeRFs) to represent videos, conducting stylization in the rendered feature space. Our innovative approach involves the simultaneous representation of both the human subject and the surrounding scene using two NeRFs. This dual representation facilitates the animation of human subjects across various poses and novel viewpoints. Specifically, we introduce a novel geometry-guided tri-plane representation, significantly enhancing feature representation robustness compared to direct tri-plane optimization. Following the video reconstruction, stylization is performed within the NeRFs' rendered feature space. Extensive experiments demonstrate that the proposed method strikes a superior balance between stylized textures and temporal coherence, surpassing existing approaches. Furthermore, our framework uniquely extends its capabilities to accommodate novel poses and viewpoints, making it a versatile tool for creative human video stylization.

cs.CV↗
arXiv2023

Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement

In this work, we explore egocentric whole-body motion capture using a single fisheye camera, which simultaneously estimates human body and hand motion. This task presents significant challenges due to three factors: the lack of high-quality datasets, fisheye camera distortion, and human body self-occlusion. To address these challenges, we propose a novel approach that leverages FisheyeViT to extract fisheye image features, which are subsequently converted into pixel-aligned 3D heatmap representations for 3D human body pose prediction. For hand tracking, we incorporate dedicated hand detection and hand pose estimation networks for regressing 3D hand poses. Finally, we develop a diffusion-based whole-body motion prior model to refine the estimated whole-body motion while accounting for joint uncertainties. To train these networks, we collect a large synthetic dataset, EgoWholeBody, comprising 840,000 high-quality egocentric images captured across a diverse range of whole-body motion sequences. Quantitative and qualitative evaluations demonstrate the effectiveness of our method in producing high-quality whole-body motion estimates from a single egocentric camera.

cs.CV↗
arXiv2023

Online Prediction of Extreme Conditional Quantiles via B-Spline Interpolation

Extreme quantiles are critical for understanding the behavior of data in the tail region of a distribution. It is challenging to estimate extreme quantiles, particularly when dealing with limited data in the tail. In such cases, extreme value theory offers a solution by approximating the tail distribution using the Generalized Pareto Distribution (GPD). This allows for the extrapolation beyond the range of observed data, making it a valuable tool for various applications. However, when it comes to conditional cases, where estimation relies on covariates, existing methods may require computationally expensive GPD fitting for different observations. This computational burden becomes even more problematic as the volume of observations increases, sometimes approaching infinity. To address this issue, we propose an interpolation-based algorithm named EMI. EMI facilitates the online prediction of extreme conditional quantiles with finite offline observations. Combining quantile regression and GPD-based extrapolation, EMI formulates as a bilevel programming problem, efficiently solvable using classic optimization methods. Once estimates for offline observations are obtained, EMI employs B-spline interpolation for covariate-dependent variables, enabling estimation for online observations with finite GPD fitting. Simulations and real data analysis demonstrate the effectiveness of EMI across various scenarios.

stat.ME↗
arXiv2023

Object Scan Context: Object-centric Spatial Descriptor for Place Recognition within 3D Point Cloud Map

The integration of a SLAM algorithm with place recognition technology empowers it with the ability to mitigate accumulated errors and to relocalize itself. However, existing methods for point cloud-based place recognition predominantly rely on the matching of descriptors, which are mostly lidar-centric. These methods suffer from two major drawbacks: first, they cannot perform place recognition when the distance between two point clouds is significant, and second, they can only calculate the rotation angle without considering the offset in the X and Y directions. To overcome these limitations, we propose a novel local descriptor that is constructed around the Main Object. By using a geometric method, we can accurately calculate the relative pose. We have provided a theoretical analysis to demonstrate that this method can overcome the aforementioned limitations. Furthermore, we conducted extensive experiments on KITTI Odometry and KITTI360, which indicate that our proposed method has significant advantages over state-of-the-art methods.

cs.CV↗
arXiv2023

Classification of spin Hall effect in two-dimensional systems

Physical properties such as the conductivity are usually classified according to the symmetry of the underlying system using Neumann's principle, which gives an upper bound for the number of independent components of the corresponding property tensor. However, for a given Hamiltonian, this global approach usually can not give a definite answer on whether a physical effect such as spin Hall effect (SHE) exists or not. It is found that the parity and types of spin-orbit interactions (SOIs) are good indicators that can further reduce the number of independent components of the spin Hall conductivity for a specific system. In terms of the parity as well as various Rashba-like and Dresselhaus-like SOIs, we propose a local approach to classify SHE in two-dimensional (2D) two-band models, where sufficient conditions for identifying the existence or absence of SHE in all 2D magnetic point groups are presented.

cond-mat.mes-hall↗
arXiv2023

Bulk-boundary-transport correspondence of the second-order topological insulators

The bulk-boundary correspondence of the second-order topological insulator (SOTI) has been well established, but a universal transport signature for open systems is still absent. For a variety of SOTIs induced by applying in-plane magnetic fields in Z$_2$-invariant first-order TIs, rotating this magnetic field features the spin pump mechanism while maintaining the SOTI phase. We demonstrate that, this spin pump can generate quantized pure spin current when tuning the magnetic field strength, which corresponds to the formation of topological corner states characterizing SOTI in two-dimensional (2D) systems. Quantized spin pump is discovered in various 2D and 3D SOTI models evolved from Z$_2$-invariant TIs, which is robust against disorder and universally independent of system parameters including Fermi energy, system size, magnetic field strength, and pumping frequency. These findings suggest that this universal quantized spin pump can characterize the bulk-boundary-transport correspondence of SOTIs. Quantized spin pump can also be realized by combining pseudo spin such as the orbital degree of freedom with the rotating magnetic field, which could be achieved in higher-order photonic or acoustic topological systems. Such a quantized spin pump is promising as an accurate and stable single-spin source.

cond-mat.mes-hall↗
arXiv2023

HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception

Model pre-training is essential in human-centric perception. In this paper, we first introduce masked image modeling (MIM) as a pre-training approach for this task. Upon revisiting the MIM training strategy, we reveal that human structure priors offer significant potential. Motivated by this insight, we further incorporate an intuitive human structure prior - human parts - into pre-training. Specifically, we employ this prior to guide the mask sampling process. Image patches, corresponding to human part regions, have high priority to be masked out. This encourages the model to concentrate more on body structure information during pre-training, yielding substantial benefits across a range of human-centric perception tasks. To further capture human characteristics, we propose a structure-invariant alignment loss that enforces different masked views, guided by the human part prior, to be closely aligned for the same image. We term the entire method as HAP. HAP simply uses a plain ViT as the encoder yet establishes new state-of-the-art performance on 11 human-centric benchmarks, and on-par result on one dataset. For example, HAP achieves 78.1% mAP on MSMT17 for person re-identification, 86.54% mA on PA-100K for pedestrian attribute recognition, 78.2% AP on MS COCO for 2D pose estimation, and 56.0 PA-MPJPE on 3DPW for 3D pose and shape estimation.

cs.CV↗
arXiv2023

A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations

Emotion recognition in conversations (ERC), the task of recognizing the emotion of each utterance in a conversation, is crucial for building empathetic machines. Existing studies focus mainly on capturing context- and speaker-sensitive dependencies on the textual modality but ignore the significance of multimodal information. Different from emotion recognition in textual conversations, capturing intra- and inter-modal interactions between utterances, learning weights between different modalities, and enhancing modal representations play important roles in multimodal ERC. In this paper, we propose a transformer-based model with self-distillation (SDT) for the task. The transformer-based model captures intra- and inter-modal interactions by utilizing intra- and inter-modal transformers, and learns weights between modalities dynamically by designing a hierarchical gated fusion strategy. Furthermore, to learn more expressive modal representations, we treat soft labels of the proposed model as extra training supervision. Specifically, we introduce self-distillation to transfer knowledge of hard and soft labels from the proposed model to each modality. Experiments on IEMOCAP and MELD datasets demonstrate that SDT outperforms previous state-of-the-art baselines.

cs.AI↗
arXiv2023

Hierarchical Memory Learning for Fine-Grained Scene Graph Generation

As far as Scene Graph Generation (SGG), coarse and fine predicates mix in the dataset due to the crowd-sourced labeling, and the long-tail problem is also pronounced. Given this tricky situation, many existing SGG methods treat the predicates equally and learn the model under the supervision of mixed-granularity predicates in one stage, leading to relatively coarse predictions. In order to alleviate the negative impact of the suboptimum mixed-granularity annotation and long-tail effect problems, this paper proposes a novel Hierarchical Memory Learning (HML) framework to learn the model from simple to complex, which is similar to the human beings' hierarchical memory learning process. After the autonomous partition of coarse and fine predicates, the model is first trained on the coarse predicates and then learns the fine predicates. In order to realize this hierarchical learning pattern, this paper, for the first time, formulates the HML framework using the new Concept Reconstruction (CR) and Model Reconstruction (MR) constraints. It is worth noticing that the HML framework can be taken as one general optimization strategy to improve various SGG models, and significant improvement can be achieved on the SGG benchmark (i.e., Visual Genome).

cs.CV↗
arXiv2023

Auslander conditions and tilting-like cotorsion pairs

We study homological behavior of modules satisfying the Auslander condition. Assume that $\mathcal{AC}$ is the class of left $R$-modules satisfying the Auslander condition. It is proved that each cycle of an exact complex with each term in $\mathcal{AC}$ belongs to $\mathcal{AC}$ for any ring $R$. As a consequence, we show that for any left Noetherian ring $R$, $\mathcal{AC}$ is a resolving subcategory of the category of left $R$-modules if and only if $_RR$ satisfies the Auslander condition if and only if each Gorenstein projective left $R$-module belongs to $\mathcal{AC}$. As an application, we prove that, for an Artinian algebra $R$ satisfying the Auslander condition, $R$ is Gorenstein if and only if $\mathcal{AC}$ coincides with the class of Gorenstein projective left $R$-modules if and only if $({\mathcal{AC}^{< \infty}},(\mathcal{AC}^{<\infty})^\bot)$ is a tilting-like cotorsion pair if and only if (${\mathcal{AC}^{< \infty}},\mathcal{I}$) is a tilting-like cotorsion pair, where $\mathcal{AC}^{<\infty}$ is the class of left $R$-modules with finite $\mathcal{AC}$-dimension and $\mathcal{I}$ is the class of injective left $R$-modules. This leads to some criteria for the validity of the Auslander and Reiten conjecture which says that an Artinian algebra satisfying the Auslander condition is Gorenstein.

math.RA↗
arXiv2023

XCloud-VIP: Virtual Peak Enables Highly Accelerated NMR Spectroscopy and Faithful Quantitative Measures

Nuclear Magnetic Resonance (NMR) spectroscopy is an important bio-engineering tool to determine the metabolic concentrations, molecule structures and so on. The data acquisition time, however, is very long in multi-dimensional NMR. To accelerate data acquisition, non-uniformly sampling is an effective way but may encounter severe spectral distortions and unfaithful quantitative measures when the acceleration factor is high. By modelling the acquired signal as the superimposed exponentials, we proposed a virtual peak (VIP) approach to selfadapt the prior spectral information, such as the resonance frequency and peak lineshape, and then feed these information into the reconstruction. The proposed method is further implemented with cloud computing to facilitate online, open, and easy access. Results on simulated and experimental data demonstrate that, compared with the low-rank Hankel matrix method, the new approach reconstructs high-fidelity NMR spectra from highly undersampled data and achieves more accurate quantification. The maximum quantitative errors of distances between nuclear pairs and concentrations of metabolites in mixtures have been reduced by 61.1% and 57.7%, respectively.

physics.med-ph↗