arXiv subjects

Xu Wang

Publications and source records attributed to Xu Wang.

At least 307 records · Page 17Linked to original sources

arXiv2023

Dataset Obfuscation: Its Applications to and Impacts on Edge Machine Learning

Obfuscating a dataset by adding random noises to protect the privacy of sensitive samples in the training dataset is crucial to prevent data leakage to untrusted parties for edge applications. We conduct comprehensive experiments to investigate how the dataset obfuscation can affect the resultant model weights - in terms of the model accuracy, Frobenius-norm (F-norm)-based model distance, and level of data privacy - and discuss the potential applications with the proposed Privacy, Utility, and Distinguishability (PUD)-triangle diagram to visualize the requirement preferences. Our experiments are based on the popular MNIST and CIFAR-10 datasets under both independent and identically distributed (IID) and non-IID settings. Significant results include a trade-off between the model accuracy and privacy level and a trade-off between the model difference and privacy level. The results indicate broad application prospects for training outsourcing in edge computing and guarding against attacks in Federated Learning among edge devices.

cs.CR↗

arXiv2023

Cross-chain between a Parent Chain and Multiple Side Chains

In certain Blockchain systems, multiple Blockchains are required to operate cooperatively for security, performance, and capacity considerations. This invention defines a cross-chain mechanism where a main Blockchain issues the tokens, which can then be transferred and used in multiple side Blockchains to drive their operations. A set of witnesses are created to securely manage the token exchange across the main chain and multiple side chains. The system decouples the consensus algorithms between the main chain and side chains. We also discuss the coexistence of the main tokens and the native tokens in the side chains.

cs.CR↗

arXiv2023

A Hybrid Wireless Image Transmission Scheme with Diffusion

We propose a hybrid joint source-channel coding (JSCC) scheme, in which the conventional digital communication scheme is complemented with a generative refinement component to improve the perceptual quality of the reconstruction. The input image is decomposed into two components: the first is a coarse compressed version, and is transmitted following the conventional separation based approach. An additional component is obtained through the diffusion process by adding independent Gaussian noise to the input image, and is transmitted using DeepJSCC. The decoder combines the two signals to produce a high quality reconstruction of the source. Experimental results show that the hybrid design provides bandwidth savings and enables graceful performance improvement as the channel quality improves.

cs.IT↗

arXiv2023

A Camera free fiber speckle wavemeter

Recovering the wavelength from disordered speckle patterns has become an exciting prospect as a wavelength measurement method due to its high resolution and simple design. In previous studies, panel cameras have been used to detect the subtle differences between speckle patterns. However, the volume, bandwidth, sensitivity, and cost (in non-visible bands) associated with panel cameras have hindered their utility in broader applications, especially in high speed and low-cost measurements. In this work, we broke the limitations imposed by panel cameras by using a quadrant detector (QD) to capture the speckle images. In the scheme of QD detection, speckle images are directly filtered by convolution, where the kernel is equal to one quarter of a speckle pattern. First, we proposed an up-sampling algorithm to pre-process the QD data. Then a new convolution neural network (CNN) based algorithm, shallow residual network (SRN), was proposed to train the up-sampled images. The experimental results show that a resolution of 4 fm (~ 0.5 MHz) was achieved at 1550nm with an updating speed of ~ 1 kHz. More importantly, the SRN shows excellent robustness. The wavelength can be precisely reconstructed from raw QD data without any averaging, even where there exists apparent noise. The low-cost, simple structure, high speed and robustness of this design promote the speckle-based wavemeter to the industrial grade. In addition, without the restriction of panel cameras, it is believed that this wavemeter opens new routes in many other fields, such as distributed optical fiber sensors, optical communications, and laser frequency stabilization.

physics.ins-det↗

arXiv2023

AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose

Creating expressive, diverse and high-quality 3D avatars from highly customized text descriptions and pose guidance is a challenging task, due to the intricacy of modeling and texturing in 3D that ensure details and various styles (realistic, fictional, etc). We present AvatarVerse, a stable pipeline for generating expressive high-quality 3D avatars from nothing but text descriptions and pose guidance. In specific, we introduce a 2D diffusion model conditioned on DensePose signal to establish 3D pose control of avatars through 2D images, which enhances view consistency from partially observed scenarios. It addresses the infamous Janus Problem and significantly stablizes the generation process. Moreover, we propose a progressive high-resolution 3D synthesis strategy, which obtains substantial improvement over the quality of the created 3D avatars. To this end, the proposed AvatarVerse pipeline achieves zero-shot 3D modeling of 3D avatars that are not only more expressive, but also in higher quality and fidelity than previous works. Rigorous qualitative evaluations and user studies showcase AvatarVerse's superiority in synthesizing high-fidelity 3D avatars, leading to a new standard in high-quality and stable 3D avatar creation. Our project page is: https://avatarverse3d.github.io

cs.CV↗

arXiv2023

Adaptive Meta-learner via Gradient Similarity for Few-shot Text Classification

Few-shot text classification aims to classify the text under the few-shot scenario. Most of the previous methods adopt optimization-based meta learning to obtain task distribution. However, due to the neglect of matching between the few amount of samples and complicated models, as well as the distinction between useful and useless task features, these methods suffer from the overfitting issue. To address this issue, we propose a novel Adaptive Meta-learner via Gradient Similarity (AMGS) method to improve the model generalization ability to a new task. Specifically, the proposed AMGS alleviates the overfitting based on two aspects: (i) acquiring the potential semantic representation of samples and improving model generalization through the self-supervised auxiliary task in the inner loop, (ii) leveraging the adaptive meta-learner via gradient similarity to add constraints on the gradient obtained by base-learner in the outer loop. Moreover, we make a systematic analysis of the influence of regularization on the entire framework. Experimental results on several benchmarks demonstrate that the proposed AMGS consistently improves few-shot text classification performance compared with the state-of-the-art optimization-based meta-learning approaches.

cs.CL↗

arXiv2023

Multi-modal Learning based Prediction for Disease

Non alcoholic fatty liver disease (NAFLD) is the most common cause of chronic liver disease, which can be predicted accurately to prevent advanced fibrosis and cirrhosis. While, a liver biopsy, the gold standard for NAFLD diagnosis, is invasive, expensive, and prone to sampling errors. Therefore, non-invasive studies are extremely promising, yet they are still in their infancy due to the lack of comprehensive research data and intelligent methods for multi-modal data. This paper proposes a NAFLD diagnosis system (DeepFLDDiag) combining a comprehensive clinical dataset (FLDData) and a multi-modal learning based NAFLD prediction method (DeepFLD). The dataset includes over 6000 participants physical examinations, laboratory and imaging studies, extensive questionnaires, and facial images of partial participants, which is comprehensive and valuable for clinical studies. From the dataset, we quantitatively analyze and select clinical metadata that most contribute to NAFLD prediction. Furthermore, the proposed DeepFLD, a deep neural network model designed to predict NAFLD using multi-modal input, including metadata and facial images, outperforms the approach that only uses metadata. Satisfactory performance is also verified on other unseen datasets. Inspiringly, DeepFLD can achieve competitive results using only facial images as input rather than metadata, paving the way for a more robust and simpler non-invasive NAFLD diagnosis.

eess.IV↗

arXiv2023

A Secure Aggregation for Federated Learning on Long-Tailed Data

As a distributed learning, Federated Learning (FL) faces two challenges: the unbalanced distribution of training data among participants, and the model attack by Byzantine nodes. In this paper, we consider the long-tailed distribution with the presence of Byzantine nodes in the FL scenario. A novel two-layer aggregation method is proposed for the rejection of malicious models and the advisable selection of valuable models containing tail class data information. We introduce the concept of think tank to leverage the wisdom of all participants. Preliminary experiments validate that the think tank can make effective model selections for global aggregation.

cs.LG↗

arXiv2023

CSCLog: A Component Subsequence Correlation-Aware Log Anomaly Detection Method

Anomaly detection based on system logs plays an important role in intelligent operations, which is a challenging task due to the extremely complex log patterns. Existing methods detect anomalies by capturing the sequential dependencies in log sequences, which ignore the interactions of subsequences. To this end, we propose CSCLog, a Component Subsequence Correlation-Aware Log anomaly detection method, which not only captures the sequential dependencies in subsequences, but also models the implicit correlations of subsequences. Specifically, subsequences are extracted from log sequences based on components and the sequential dependencies in subsequences are captured by Long Short-Term Memory Networks (LSTMs). An implicit correlation encoder is introduced to model the implicit correlations of subsequences adaptively. In addition, Graph Convolution Networks (GCNs) are employed to accomplish the information interactions of subsequences. Finally, attention mechanisms are exploited to fuse the embeddings of all subsequences. Extensive experiments on four publicly available log datasets demonstrate the effectiveness of CSCLog, outperforming the best baseline by an average of 7.41% in Macro F1-Measure.

cs.LG↗

arXiv2023

Automated 3D Pre-Training for Molecular Property Prediction

Molecular property prediction is an important problem in drug discovery and materials science. As geometric structures have been demonstrated necessary for molecular property prediction, 3D information has been combined with various graph learning methods to boost prediction performance. However, obtaining the geometric structure of molecules is not feasible in many real-world applications due to the high computational cost. In this work, we propose a novel 3D pre-training framework (dubbed 3D PGT), which pre-trains a model on 3D molecular graphs, and then fine-tunes it on molecular graphs without 3D structures. Based on fact that bond length, bond angle, and dihedral angle are three basic geometric descriptors corresponding to a complete molecular 3D conformer, we first develop a multi-task generative pre-train framework based on these three attributes. Next, to automatically fuse these three generative tasks, we design a surrogate metric using the \textit{total energy} to search for weight distribution of the three pretext task since total energy corresponding to the quality of 3D conformer.Extensive experiments on 2D molecular graphs are conducted to demonstrate the accuracy, efficiency and generalization ability of the proposed 3D PGT compared to various pre-training baselines.

q-bio.QM↗

arXiv2023

DRAN: Detailed Region-Adaptive Normalization for Conditional Image Synthesis

In recent years, conditional image synthesis has attracted growing attention due to its controllability in the image generation process. Although recent works have achieved realistic results, most of them have difficulty handling fine-grained styles with subtle details. To address this problem, a novel normalization module, named Detailed Region-Adaptive Normalization~(DRAN), is proposed. It adaptively learns both fine-grained and coarse-grained style representations. Specifically, we first introduce a multi-level structure, Spatiality-aware Pyramid Pooling, to guide the model to learn coarse-to-fine features. Then, to adaptively fuse different levels of styles, we propose Dynamic Gating, making it possible to adaptively fuse different levels of styles according to different spatial regions. Finally, we collect a new makeup dataset (Makeup-Complex dataset) that contains a wide range of complex makeup styles with diverse poses and expressions. To evaluate the effectiveness and show the general use of our method, we conduct a set of experiments on makeup transfer and semantic image synthesis. Quantitative and qualitative experiments show that equipped with DRAN, simple baseline models are able to achieve promising improvements in complex style transfer and detailed texture synthesis. Both the code and the proposed dataset will be available at https://github.com/Yueming6568/DRAN-makeup.git.

cs.CV↗

arXiv2023

Quantum theory of isomeric excitation of $^{229}$Th in strong laser fields

A general quantum mechanical theory is developed for the isomeric excitation of $^{229}$Th in strong femtosecond laser pulses. The theory describes the tripartite interaction between the nucleus, the atomic electrons, and the laser field. The nucleus can be excited both by the laser field and by laser-driven electronic transitions. Numerical results show that strong femtosecond laser pulses are very efficient in exciting the $^{229}$Th nucleus, yielding nuclear excitation probabilities on the order of $10^{-11}$ per nucleus per pulse. Laser-driven electronic excitations are found to be more efficient than direct optical excitations.

nucl-th↗

arXiv2023

Research on Named Entity Recognition in Improved transformer with R-Drop structure

To enhance the generalization ability of the model and improve the effectiveness of the transformer for named entity recognition tasks, the XLNet-Transformer-R model is proposed in this paper. The XLNet pre-trained model and the Transformer encoder with relative positional encodings are combined to enhance the model's ability to process long text and learn contextual information to improve robustness. To prevent overfitting, the R-Drop structure is used to improve the generalization capability and enhance the accuracy of the model in named entity recognition tasks. The model in this paper performs ablation experiments on the MSRA dataset and comparison experiments with other models on four datasets with excellent performance, demonstrating the strategic effectiveness of the XLNet-Transformer-R model.

cs.CL↗

arXiv2023

Research on an improved Conformer end-to-end Speech Recognition Model with R-Drop Structure

To address the issue of poor generalization ability in end-to-end speech recognition models within deep learning, this study proposes a new Conformer-based speech recognition model called "Conformer-R" that incorporates the R-drop structure. This model combines the Conformer model, which has shown promising results in speech recognition, with the R-drop structure. By doing so, the model is able to effectively model both local and global speech information while also reducing overfitting through the use of the R-drop structure. This enhances the model's ability to generalize and improves overall recognition efficiency. The model was first pre-trained on the Aishell1 and Wenetspeech datasets for general domain adaptation, and subsequently fine-tuned on computer-related audio data. Comparison tests with classic models such as LAS and Wenet were performed on the same test set, demonstrating the Conformer-R model's ability to effectively improve generalization.

cs.SD↗

arXiv2023

Gaussian Gabor frames, Seshadri constants and generalized Buser--Sarnak invariants

We investigate the frame set of regular multivariate Gaussian Gabor frames using methods from Kähler geometry such as Hörmander's $\dbar$-$L^2$ estimate with singular weight, Demailly's Calabi--Yau method for Kähler currents and a Kähler-variant generalization of the symplectic embedding theorem of McDuff--Polterovich for ellipsoids. Our approach is based on the well-known link between sets of interpolation for the Bargmann-Fock space and the frame set of multivariate Gaussian Gabor frames. We state sufficient conditions in terms of a certain extremal type Seshadri constant of the complex torus associated to a lattice to be a set of interpolation for the Bargmann-Fock space, and give also a condition in terms of the generalized Buser-Sarnak invariant of the lattice. In particular, we obtain an effective Gaussian Gabor frame criterion in terms of the covolume for almost all lattices, which is the first general covolume criterion in multivariate Gaussian Gabor frame theory. The recent Berndtsson--Lempert method and the Ohsawa--Takegoshi extension theorem also allow us to give explicit estimates for the frame bounds in terms of certain Robin constant. In the one-dimensional case we obtain a sharp estimate of the Robin constant using Faltings' theta metric formula for the Arakelov Green functions.

math.CV↗

arXiv2023

DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade

In the constant updates of the product dialogue systems, we need to retrain the natural language understanding (NLU) model as new data from the real users would be merged into the existent data accumulated in the last updates. Within the newly added data, new intents would emerge and might have semantic entanglement with the existing intents, e.g. new intents that are semantically too specific or generic are actually subset or superset of some existing intents in the semantic space, thus impairing the robustness of the NLU model. As the first attempt to solve this problem, we setup a new benchmark consisting of 4 Dialogue Version Control dataSets (DialogVCS). We formulate the intent detection with imperfect data in the system update as a multi-label classification task with positive but unlabeled intents, which asks the models to recognize all the proper intents, including the ones with semantic entanglement, in the inference. We also propose comprehensive baseline models and conduct in-depth analyses for the benchmark, showing that the semantically entangled intents can be effectively recognized with an automatic workflow.

cs.CL↗

arXiv2023

Blockchained Federated Learning for Internet of Things: A Comprehensive Survey

The demand for intelligent industries and smart services based on big data is rising rapidly with the increasing digitization and intelligence of the modern world. This survey comprehensively reviews Blockchained Federated Learning (BlockFL) that joins the benefits of both Blockchain and Federated Learning to provide a secure and efficient solution for the demand. We compare the existing BlockFL models in four Internet-of-Things (IoT) application scenarios: Personal IoT (PIoT), Industrial IoT (IIoT), Internet of Vehicles (IoV), and Internet of Health Things (IoHT), with a focus on security and privacy, trust and reliability, efficiency, and data heterogeneity. Our analysis shows that the features of decentralization and transparency make BlockFL a secure and effective solution for distributed model training, while the overhead and compatibility still need further study. It also reveals the unique challenges of each domain presents unique challenges, e.g., the requirement of accommodating dynamic environments in IoV and the high demands of identity and permission management in IoHT, in addition to some common challenges identified, such as privacy, resource constraints, and data heterogeneity. Furthermore, we examine the existing technologies that can benefit BlockFL, thereby helping researchers and practitioners to make informed decisions about the selection and development of BlockFL for various IoT application scenarios.

cs.LG↗

arXiv2023

Point Transformer For Coronary Artery Labeling

Coronary CT angiography (CCTA) scans are widely used for diagnosis of coronary artery diseases. An accurate and automatic vessel labeling algorithm for CCTA analysis can significantly improve the diagnostic efficiency and reduce the clinicians'manual efforts. In this paper, we propose a simple vessel labeling method based on the Point Transformer, which only needs the coronary artery segmentation. Specifically, firstly, the coronary segmentation is transformed to point cloud. Then, these points are fed into the hierarchical transformer blocks to obtain the multi-level features, including local and global features. Finally, the network output the semantic classification points and map them to centerline labeling. This method is only based on the structure of coronary segmentation and need not other features, so it is easy to generalize to other vessel labeling tasks, e.g., head and neck vessel labeling. To evaluate the performance of our proposed method, CCTA scans of 53 subjects are collected in our experiment. The experimental results demonstrate the efficacy of this approach.

eess.IV↗