arXiv subjects

Wei Huang

Publications and source records attributed to Wei Huang.

At least 361 records · Page 20Linked to original sources

arXiv2022

Secure two-way fiber-optic time transfer against sub-ns asymmetric delay attack

Two-way fiber-optic time transfer is a promising precise time synchronization technique with sub-nanosecond accuracy. However, asymmetric delay attack is a serious threat which cannot be prevent by any encryption method. In this paper, a dynamic model based scheme is proposed to defense the sub-nanosecond asymmetric delay attack. A threshold is set according to the estimated time difference by a two-state clock model where the fixed frequency difference is excluded from the time difference to detect the asymmetric delay attack which is smaller than the time difference induced by the fixed frequency difference. Theoretical simulation and experimental demonstration are implemented to prove the feasibility of the scheme. A two-way fiber-optic time transfer system with time stability with 24.5ps, 3.98ps, and 2.95ps at 1s, 10s, and 100s averaging time is shown under sub-ns asymmetric time delay attack experimentally. The proposed method provides a promising secure sub-ns precise time synchronization technique against asymmetric delay attack.

quant-ph↗

arXiv2022

Attention-Based Lip Audio-Visual Synthesis for Talking Face Generation in the Wild

Talking face generation with great practical significance has attracted more attention in recent audio-visual studies. How to achieve accurate lip synchronization is a long-standing challenge to be further investigated. Motivated by xxx, in this paper, an AttnWav2Lip model is proposed by incorporating spatial attention module and channel attention module into lip-syncing strategy. Rather than focusing on the unimportant regions of the face image, the proposed AttnWav2Lip model is able to pay more attention on the lip region reconstruction. To our limited knowledge, this is the first attempt to introduce attention mechanism to the scheme of talking face generation. An extensive experiments have been conducted to evaluate the effectiveness of the proposed model. Compared to the baseline measured by LSE-D and LSE-C metrics, a superior performance has been demonstrated on the benchmark lip synthesis datasets, including LRW, LRS2 and LRS3.

cs.CV↗

arXiv2022

Audio-visual speech separation based on joint feature representation with cross-modal attention

Multi-modal based speech separation has exhibited a specific advantage on isolating the target character in multi-talker noisy environments. Unfortunately, most of current separation strategies prefer a straightforward fusion based on feature learning of each single modality, which is far from sufficient consideration of inter-relationships between modalites. Inspired by learning joint feature representations from audio and visual streams with attention mechanism, in this study, a novel cross-modal fusion strategy is proposed to benefit the whole framework with semantic correlations between different modalities. To further improve audio-visual speech separation, the dense optical flow of lip motion is incorporated to strengthen the robustness of visual representation. The evaluation of the proposed work is performed on two public audio-visual speech separation benchmark datasets. The overall improvement of the performance has demonstrated that the additional motion network effectively enhances the visual representation of the combined lip images and audio signal, as well as outperforming the baseline in terms of all metrics with the proposed cross-modal fusion.

cs.SD↗

arXiv2022

Auto-scaling Vision Transformers without Training

This work targets automated designing and scaling of Vision Transformers (ViTs). The motivation comes from two pain spots: 1) the lack of efficient and principled methods for designing and scaling ViTs; 2) the tremendous computational cost of training ViT that is much heavier than its convolution counterpart. To tackle these issues, we propose As-ViT, an auto-scaling framework for ViTs without training, which automatically discovers and scales up ViTs in an efficient and principled manner. Specifically, we first design a "seed" ViT topology by leveraging a training-free search process. This extremely fast search is fulfilled by a comprehensive study of ViT's network complexity, yielding a strong Kendall-tau correlation with ground-truth accuracies. Second, starting from the "seed" topology, we automate the scaling rule for ViTs by growing widths/depths to different ViT layers. This results in a series of architectures with different numbers of parameters in a single run. Finally, based on the observation that ViTs can tolerate coarse tokenization in early training stages, we propose a progressive tokenization strategy to train ViTs faster and cheaper. As a unified framework, As-ViT achieves strong performance on classification (83.5% top1 on ImageNet-1k) and detection (52.7% mAP on COCO) without any manual crafting nor scaling of ViT architectures: the end-to-end model design and scaling process cost only 12 hours on one V100 GPU. Our code is available at https://github.com/VITA-Group/AsViT.

cs.LG↗

arXiv2022

Achieving Efficient Distributed Machine Learning Using a Novel Non-Linear Class of Aggregation Functions

Distributed machine learning (DML) over time-varying networks can be an enabler for emerging decentralized ML applications such as autonomous driving and drone fleeting. However, the commonly used weighted arithmetic mean model aggregation function in existing DML systems can result in high model loss, low model accuracy, and slow convergence speed over time-varying networks. To address this issue, in this paper, we propose a novel non-linear class of model aggregation functions to achieve efficient DML over time-varying networks. Instead of taking a linear aggregation of neighboring models as most existing studies do, our mechanism uses a nonlinear aggregation, a weighted power-p mean (WPM), as the aggregation function of local models from neighbors. The subsequent optimizing steps are taken using mirror descent defined by a Bregman divergence that maintains convergence to optimality. In this paper, we analyze properties of the WPM and rigorously prove convergence properties of our aggregation mechanism. Additionally, through extensive experiments, we show that when p > 1, our design significantly improves the convergence speed of the model and the scalability of DML under time-varying networks compared with arithmetic mean aggregation functions, with little additional computation overhead.

cs.LG↗

arXiv2022

Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning

PAC-Bayesian is an analysis framework where the training error can be expressed as the weighted average of the hypotheses in the posterior distribution whilst incorporating the prior knowledge. In addition to being a pure generalization bound analysis tool, PAC-Bayesian bound can also be incorporated into an objective function to train a probabilistic neural network, making them a powerful and relevant framework that can numerically provide a tight generalization bound for supervised learning. For simplicity, we call probabilistic neural network learned using training objectives derived from PAC-Bayesian bounds as {\it PAC-Bayesian learning}. Despite their empirical success, the theoretical analysis of PAC-Bayesian learning for neural networks is rarely explored. This paper proposes a new class of convergence and generalization analysis for PAC-Bayes learning when it is used to train the over-parameterized neural networks by the gradient descent method. For a wide probabilistic neural network, we show that when PAC-Bayes learning is applied, the convergence result corresponds to solving a kernel ridge regression when the probabilistic neural tangent kernel (PNTK) is used as its kernel. Based on this finding, we further characterize the uniform PAC-Bayesian generalization bound which improves over the Rademacher complexity-based bound for non-probabilistic neural network. Finally, drawing the insight from our theoretical results, we propose a proxy measure for efficient hyperparameters selection, which is proven to be time-saving.

cs.LG↗

arXiv2022

Knowledge Graph Based Waveform Recommendation: A New Communication Waveform Design Paradigm

Traditionally, a communication waveform is designed by experts based on communication theory and their experiences on a case-by-case basis, which is usually laborious and time-consuming. In this paper, we investigate the waveform design from a novel perspective and propose a new waveform design paradigm with the knowledge graph (KG)-based intelligent recommendation system. The proposed paradigm aims to improve the design efficiency by structural characterization and representations of existing waveforms and intelligently utilizing the knowledge learned from them. To achieve this goal, we first build a communication waveform knowledge graph (CWKG) with a first-order neighbor node, for which both structured semantic knowledge and numerical parameters of a waveform are integrated by representation learning. Based on the developed CWKG, we further propose an intelligent communication waveform recommendation system (CWRS) to generate waveform candidates. In the CWRS, an improved involution1D operator, which is channel-agnostic and space-specific, is introduced according to the characteristics of KG-based waveform representation for feature extraction, and the multi-head self-attention is adopted to weigh the influence of various components for feature fusion. Meanwhile, multilayer perceptron-based collaborative filtering is used to evaluate the matching degree between the requirement and the waveform candidate. Simulation results show that the proposed CWKG-based CWRS can automatically recommend waveform candidates with high reliability.

eess.SP↗

arXiv2021

Coupling-assisted quasi-bound states in the continuum in heterogeneous metasurfaces

In this paper, we present a Bound states in the continuum (BIC) metamaterial in heterogeneous structures based on the universal coupled mode theory. We find the more general physical parameters to represent BIC, which are the resonant frequencies and corresponding phases of metamaterial structures. Therefore, BIC metamaterial comes from the equal value of the resonant frequencies and phases of metamaterial structures which are not only for homogeneous structures. Meanwhile if slightly vary one of metamaterial structure's resonant frequency and phase by varying geometry, we can obtain the quasi-BIC instead of broken symmetry of homogeneous structures. In this paper, we provide the BIC and quasi-BIC with one example of two heterogeneous structures which are cut wire (CW) and Split-Ring Resonator (SRR), to widely extends the metamaterial BIC beyond common sense. Furthermore, we demonstrate the simulation results and experimental results to proof our idea.

physics.optics↗

arXiv2021

Semantic-Aware Generation for Self-Supervised Visual Representation Learning

In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by requiring the target network to recover the original image based on the mid-level features. Different from prior work that mostly focuses on pixel-level similarity between the original and generated images, we advocate for Semantic-aware Generation (SaGe) to facilitate richer semantics rather than details to be preserved in the generated image. The core idea of implementing SaGe is to use an evaluator, a deep network that is pre-trained without labels, for extracting semantic-aware features. SaGe complements the target network with view-specific features and thus alleviates the semantic degradation brought by intensive data augmentations. We execute SaGe on ImageNet-1K and evaluate the pre-trained models on five downstream tasks including nearest neighbor test, linear classification, and fine-scaled image recognition, demonstrating its ability to learn stronger visual representations.

cs.CV↗

arXiv2021

Sub-Gbps key rate four-state continuous-variable quantum key distribution within metropolitan area

Continuous-variable quantum key distribution (CVQKD) has potential advantages of high secret key rate, which is very suitable for high-speed metropolitan network application. However, the reported highest secret key rates of the CVQKD systems up to now are limited in a few Mbps. Here, we address the fundamental experimental problems and demonstrate a single-carrier four-state CVQKD with sub-Gbps key rate within metropolitan area. In the demonstrated four-state CVQKD using local local oscillator, an ultra-low level of excess noise is obtained and a high efficient post-processing setup is designed for practically extracting the final secure keys. Thus, the achieved secure key rates are 190.54 Mbps and 137.76 Mbps and 52.48 Mbps using linear channel assuming security analysis method and 233.87 Mbps, 133.6 Mbps and 21.53 Mbps using semidefinite programming security analysis method over transmission distances of 5 km, 10 km and 25 km, respectively. This record-breaking result increases the previous secret key rate record by an order of magnitude, which is sufficient to achieve the one-time pad cryptographic task. Our work shows the road for future high-rate and large-scale CVQKD deployment in secure broadband metropolitan and access networks.

quant-ph↗

arXiv2021

Phase-reference intensity attack on continuous-variable quantum key distribution with a real local oscillator

In practical continuous-variable quantum key distribution system using local local oscillator (LLO CV-QKD), the phase noise related to coherent detection and phase-reference pulse intensity that can be locally calibrated at the receiver side is considered to be trusted noise to improve the performance. However, if the intensity of the phase-reference pulse is not monitored precisely in real-time, a security loophole will be opened for the eavesdropper to launch attacks. To this end, we propose two practical phase-reference pulse intensity attack strategies, where Eve can reduce the trusted phase noise by manipulating the intensity of the phase-reference pulse, thereby hiding her attack on the signal pulse if the total excess noise remains unchanged. The performance of the LLO CV-QKD system under these attacks has been analyzed. We show that precisely monitoring the intensity of the phase-reference pulse in real-time is an essential countermeasure to prevent the proposed attacks. Moreover, an intensity-monitoring scheme for the phase-reference pulse is proposed to strengthen the security of the practical LLO CV-QKD system and make the trusted phase noise model more robust.

quant-ph↗

arXiv2021

Towards fully ab initio simulation of atmospheric aerosol nucleation

Atmospheric aerosol nucleation contributes to more than half of cloud condensation nuclei globally. The emissions, properties and concentrations of atmospheric aerosols or aerosol precursors could respond significantly to climate change. Despite the importance for climate, the detailed nucleation mechanisms are still poorly understood. The ultimate goal of theoretical understanding aerosol nucleation is to simulate nucleation in ambient condition, hindered by lack of accurate reactive force field. Here we propose the reactive force field for nucleation systems with good size scalability based on deep neural network. The huge computational costs from direct molecular dynamics in ambient conditions are surmounted by bridging the simulation in the limited box with cluster kinetics, facilitating the aerosol nucleation simulation to be fully ab initio. We found that the acid-base formation rates previously based on hard sphere collision rate constants tend to be underestimated up to several times. These findings show that the widely recognized acid-base nucleation observed in the CLOUD (Cosmics Leaving OUtdoor Droplets) chamber experiments, pristine and polluted environments should be revisited to considering the contribution of collision enhancement. Besides, the framework here is transferable to other nucleation systems, potentially boosting the nucleation parameterizations accuracy generally to effectively advance the climate model predictions reliability.

physics.atm-clus↗

arXiv2021

Embedding and Extraction of Knowledge in Tree Ensemble Classifiers

The embedding and extraction of useful knowledge is a recent trend in machine learning applications, e.g., to supplement existing datasets that are small. Whilst, as the increasing use of machine learning models in security-critical applications, the embedding and extraction of malicious knowledge are equivalent to the notorious backdoor attack and its defence, respectively. This paper studies the embedding and extraction of knowledge in tree ensemble classifiers, and focuses on knowledge expressible with a generic form of Boolean formulas, e.g., robustness properties and backdoor attacks. For the embedding, it is required to be preservative(the original performance of the classifier is preserved), verifiable(the knowledge can be attested), and stealthy(the embedding cannot be easily detected). To facilitate this, we propose two novel, and effective, embedding algorithms, one of which is for black-box settings and the other for white-box settings.The embedding can be done in PTIME. Beyond the embedding, we develop an algorithm to extract the embedded knowledge, by reducing the problem to be solvable with an SMT (satisfiability modulo theories) solver. While this novel algorithm can successfully extract knowledge, the reduction leads to an NP computation. Therefore, if applying embedding as backdoor attacks and extraction as defence, our results suggest a complexity gap (P vs. NP) between the attack and defence when working with tree ensemble classifiers. We apply our algorithms toa diverse set of datasets to validate our conclusion extensively.

cs.CR↗

arXiv2021

Long-tailed Distribution Adaptation

Recognizing images with long-tailed distributions remains a challenging problem while there lacks an interpretable mechanism to solve this problem. In this study, we formulate Long-tailed recognition as Domain Adaption (LDA), by modeling the long-tailed distribution as an unbalanced domain and the general distribution as a balanced domain. Within the balanced domain, we propose to slack the generalization error bound, which is defined upon the empirical risks of unbalanced and balanced domains and the divergence between them. We propose to jointly optimize empirical risks of the unbalanced and balanced domains and approximate their domain divergence by intra-class and inter-class distances, with the aim to adapt models trained on the long-tailed distribution to general distributions in an interpretable way. Experiments on benchmark datasets for image recognition, object detection, and instance segmentation validate that our LDA approach, beyond its interpretability, achieves state-of-the-art performance. Code is available at https://github.com/pengzhiliang/LDA.

cs.CV↗

arXiv2021

Hierarchy-Aware T5 with Path-Adaptive Mask Mechanism for Hierarchical Text Classification

Hierarchical Text Classification (HTC), which aims to predict text labels organized in hierarchical space, is a significant task lacking in investigation in natural language processing. Existing methods usually encode the entire hierarchical structure and fail to construct a robust label-dependent model, making it hard to make accurate predictions on sparse lower-level labels and achieving low Macro-F1. In this paper, we propose a novel PAMM-HiA-T5 model for HTC: a hierarchy-aware T5 model with path-adaptive mask mechanism that not only builds the knowledge of upper-level labels into low-level ones but also introduces path dependency information in label prediction. Specifically, we generate a multi-level sequential label structure to exploit hierarchical dependency across different levels with Breadth-First Search (BFS) and T5 model. To further improve label dependency prediction within each path, we then propose an original path-adaptive mask mechanism (PAMM) to identify the label's path information, eliminating sources of noises from other paths. Comprehensive experiments on three benchmark datasets show that our novel PAMM-HiA-T5 model greatly outperforms all state-of-the-art HTC approaches especially in Macro-F1. The ablation studies show that the improvements mainly come from our innovative approach instead of T5.

cs.CL↗

arXiv2021

Phase Noise Model for Continuous-Variable Quantum Key Distribution Using a Local Local Oscillator

The value of residual phase noise, after phase compensation, is one of the key limitations of performance improvement for continuous-variable quantum key distribution using a local local oscillator (LLO CV-QKD) system, since it is the major excess noise. However, due to the non-ideality of the realistic devices implemented in practice, for example, imperfect lasers, detectors and unbalanced interferometers, the value of residual phase noise in current system is still relatively large. Here, we develop a phase noise model to improve the phase noise tolerance of the LLO CV-QKD schemes. In our model, part of the phase-reference measurement noise associated with detection efficiency and electronic noise of Bob's detector as well as a real-time monitored phasereference intensity at Bob's side is considered trusted because it can be locally calibrated by Bob. We show that using our phase noise model can significantly improve the secure key rate and transmission distance of the LLO CV-QKD system. We further conduct an experiment to substantiate the superiority of the phase noise model. Based on experimental data of a LLO CV-QKD system in the 25 km optical fiber channel, we demonstrate that the secure key rate under our phase noise model is approximately 40% higher than that under the conventional phase noise model.

quant-ph↗

arXiv2021

Euclidean Algebras

We introduce a new example of unital commutative $n$-dimensional group algebra $\mathbb{R}_n$ for $n \geq 2$. The algebra $\mathbb{R}_n$ and the complex numbers $\mathbb{C}$ are astonishingly alike. The zero divisor set of the algebra has Lebesgue $μ_n$-measure zero. The formula for the Haar measure is established. Also, the analytic function theory in $\mathbb{R}_n,$ for $n=2k$ that similar to the classical theory in $\mathbb{C}$ is introduced. This includes the Cauchy-Riemann equations, mean-value theorem and Louisville theorem.

math.FA↗

arXiv2021

A Unified Framework for Specification Tests of Continuous Treatment Effect Models

We propose a general framework for the specification testing of continuous treatment effect models. We assume a general residual function, which includes the average and quantile treatment effect models as special cases. The null models are identified under the unconfoundedness condition and contain a nonparametric weighting function. We propose a test statistic for the null model in which the weighting function is estimated by solving an expanding set of moment equations. We establish the asymptotic distributions of our test statistic under the null hypothesis and under fixed and local alternatives. The proposed test statistic is shown to be more efficient than that constructed from the true weighting function and can detect local alternatives deviated from the null models at the rate of $O(N^{-1/2})$. A simulation method is provided to approximate the null distribution of the test statistic. Monte-Carlo simulations show that our test exhibits a satisfactory finite-sample performance, and an application shows its practical value.

econ.EM↗