arXiv subjects

Ning Chen

Publications and source records attributed to Ning Chen.

At least 73 records · Page 4Linked to original sources

arXiv2023

Improving Viewpoint Robustness for Visual Recognition via Adversarial Training

Viewpoint invariance remains challenging for visual recognition in the 3D world, as altering the viewing directions can significantly impact predictions for the same object. While substantial efforts have been dedicated to making neural networks invariant to 2D image translations and rotations, viewpoint invariance is rarely investigated. Motivated by the success of adversarial training in enhancing model robustness, we propose Viewpoint-Invariant Adversarial Training (VIAT) to improve the viewpoint robustness of image classifiers. Regarding viewpoint transformation as an attack, we formulate VIAT as a minimax optimization problem, where the inner maximization characterizes diverse adversarial viewpoints by learning a Gaussian mixture distribution based on the proposed attack method GMVFool. The outer minimization obtains a viewpoint-invariant classifier by minimizing the expected loss over the worst-case viewpoint distributions that can share the same one for different objects within the same category. Based on GMVFool, we contribute a large-scale dataset called ImageNet-V+ to benchmark viewpoint robustness. Experimental results show that VIAT significantly improves the viewpoint robustness of various image classifiers based on the diversity of adversarial viewpoints generated by GMVFool. Furthermore, we propose ViewRS, a certified viewpoint robustness method that provides a certified radius and accuracy to demonstrate the effectiveness of VIAT from the theoretical perspective.

cs.CV↗

arXiv2023

Towards Viewpoint-Invariant Visual Recognition via Adversarial Training

Visual recognition models are not invariant to viewpoint changes in the 3D world, as different viewing directions can dramatically affect the predictions given the same object. Although many efforts have been devoted to making neural networks invariant to 2D image translations and rotations, viewpoint invariance is rarely investigated. As most models process images in the perspective view, it is challenging to impose invariance to 3D viewpoint changes based only on 2D inputs. Motivated by the success of adversarial training in promoting model robustness, we propose Viewpoint-Invariant Adversarial Training (VIAT) to improve viewpoint robustness of common image classifiers. By regarding viewpoint transformation as an attack, VIAT is formulated as a minimax optimization problem, where the inner maximization characterizes diverse adversarial viewpoints by learning a Gaussian mixture distribution based on a new attack GMVFool, while the outer minimization trains a viewpoint-invariant classifier by minimizing the expected loss over the worst-case adversarial viewpoint distributions. To further improve the generalization performance, a distribution sharing strategy is introduced leveraging the transferability of adversarial viewpoints across objects. Experiments validate the effectiveness of VIAT in improving the viewpoint robustness of various image classifiers based on the diversity of adversarial viewpoints generated by GMVFool.

cs.CV↗

arXiv2023

Automatic Speech Disentanglement for Voice Conversion using Rank Module and Speech Augmentation

Voice Conversion (VC) converts the voice of a source speech to that of a target while maintaining the source's content. Speech can be mainly decomposed into four components: content, timbre, rhythm and pitch. Unfortunately, most related works only take into account content and timbre, which results in less natural speech. Some recent works are able to disentangle speech into several components, but they require laborious bottleneck tuning or various hand-crafted features, each assumed to contain disentangled speech information. In this paper, we propose a VC model that can automatically disentangle speech into four components using only two augmentation functions, without the requirement of multiple hand-crafted features or laborious bottleneck tuning. The proposed model is straightforward yet efficient, and the empirical results demonstrate that our model can achieve a better performance than the baseline, regarding disentanglement effectiveness and speech naturalness.

cs.SD↗

arXiv2023

First Principles and Machine Learning Identify Key Pairing Strength Factors of Cuprate Superconductors

By using band structure calculations of quantum mechanical theory, some important peaks of DoS (Density of States) were obtained and classified based on crystal structure laws of cuprate superconductivity. In particular, the orbital interactions of the in-plane and out-of-plane ions of the copper-oxygen plane were investigated. The position, half-width, and height of DOS peak features were collected for all 35 typical curate systems which have critical temperature maximum data from the works of literature. By training test of 7 common machine learning algorithms, the relationship between the Tc maximum values and these orbital interaction parameters were mined. It was found that the key features of the orbital interaction affecting the Tc maximum were not only the flat band but also a new interaction between core orbitals in a deeper energy band position.

cond-mat.supr-con↗

arXiv2023

A two-generational ${\rm SU}(7)$ model with extended weak sector: mass hierarchies, mixings, and the flavor non-universality

We study a possible gauge symmetry breaking pattern in an ${\rm SU}(7)$ grand unified theory, which describes the mass origins of all electrically charged SM fermions of the second and the third generations. Two intermediate gauge symmetries of ${\cal G}_{341}\equiv {\rm SU}(3)_c \otimes {\rm SU}(4)_W \otimes {\rm U}(1)_{X_0}$ and ${\cal G}_{331}\equiv {\rm SU}(3)_c \otimes {\rm SU}(3)_W \otimes {\rm U}(1)_{X_1}$ arise above the electroweak scale. SM fermion mass hierarchies between two generations can be obtained through a generalized seesaw mechanism. The mechanism can be achieved with suppressed symmetry breaking VEVs from multiple Higgs fields that are necessary to avoid tadpole terms in the Higgs potential. Some general features of the ${\rm SU}(7)$ fermion spectrum will be described, which include the existence of vectorlike fermions, the tree-level flavor changing weak currents between the SM fermions and heavy partner fermions, and the flavor non-universality between different SM generations from the extended weak sector.

hep-ph↗

arXiv2023

Bottom quark and tau lepton masses in a toy ${\rm SU}(6)$

We study a toy ${\rm SU}(6)$ model with the symmetry breaking pattern of the extended $331$ symmetry of ${\rm SU}(3)_c \otimes {\rm SU}(3)_W \otimes {\rm U}(1)_X$. A "fermion-Higgs mismatching" symmetry breaking pattern is proposed for more realistic model building. Within such symmetry breaking pattern, only one Higgs doublet develops vacuum expectation value for the spontaneous electroweak symmetry breaking, and gives tree-level top quark mass. A natural VEV splittings in the $331$ breaking Higgs fields gives tree-level masses to both bottom quark and tau lepton. The $125\,{\rm GeV}$ SM-like Higgs boson discovered at the LHC can have Yukawa couplings to bottom quark and tau lepton as in the SM prediction, and this suggests the $331$ symmetry breaking scale to be $\sim {\cal O}(10)\,{\rm TeV}$.

hep-ph↗

arXiv2023

Investigation of Cu-site disorder in undoped and doped BiCuSeO

We carried out X-ray diffraction and Extended X-ray Absorption Fine Structure (EXAFS) studies to investigate the origin of the low lattice thermal conductivity in BiCuSeO, and the role of silver (Ag) doping in doped samples. BiCuSeO is a promising thermoelectric material with high thermoelectric efficiency, which is significantly enhanced by doping either single Ag dopants or dual dopants (Pb and Ag). We verified that the thermal displacement parameters associated with copper (Cu) are significantly large in undoped BiCuSeO. Ag dopant, which replaces Cu, was also found to have similarly large thermal displacement parameters, that remain large down to low temperatures. Our results point towards significant disorder on Cu-site in both undoped and doped BiCuSeO, which is retained by Ag dopant on replacing Cu. The disorder is observed to be localized on the Cu-site and seems to be independent of other atoms in the crystal structure. Our observation of the disorder, which could be either static or quasi-static, is consistent with a rattling mode scenario.

cond-mat.mtrl-sci↗

arXiv2023

Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition

Face recognition is a prevailing authentication solution in numerous biometric applications. Physical adversarial attacks, as an important surrogate, can identify the weaknesses of face recognition systems and evaluate their robustness before deployed. However, most existing physical attacks are either detectable readily or ineffective against commercial recognition systems. The goal of this work is to develop a more reliable technique that can carry out an end-to-end evaluation of adversarial robustness for commercial systems. It requires that this technique can simultaneously deceive black-box recognition models and evade defensive mechanisms. To fulfill this, we design adversarial textured 3D meshes (AT3D) with an elaborate topology on a human face, which can be 3D-printed and pasted on the attacker's face to evade the defenses. However, the mesh-based optimization regime calculates gradients in high-dimensional mesh space, and can be trapped into local optima with unsatisfactory transferability. To deviate from the mesh-based space, we propose to perturb the low-dimensional coefficient space based on 3D Morphable Model, which significantly improves black-box transferability meanwhile enjoying faster search efficiency and better visual quality. Extensive experiments in digital and physical scenarios show that our method effectively explores the security vulnerabilities of multiple popular commercial services, including three recognition APIs, four anti-spoofing APIs, two prevailing mobile phones and two automated access control systems.

cs.CV↗

arXiv2022

Learning-Based Client Selection for Federated Learning Services Over Wireless Networks with Constrained Monetary Budgets

We investigate a data quality-aware dynamic client selection problem for multiple federated learning (FL) services in a wireless network, where each client offers dynamic datasets for the simultaneous training of multiple FL services, and each FL service demander has to pay for the clients under constrained monetary budgets. The problem is formalized as a non-cooperative Markov game over the training rounds. A multi-agent hybrid deep reinforcement learning-based algorithm is proposed to optimize the joint client selection and payment actions, while avoiding action conflicts. Simulation results indicate that our proposed algorithm can significantly improve training performance.

cs.LG↗

arXiv2022

A Survey on Ensemble Learning under the Era of Deep Learning

Due to the dominant position of deep learning (mostly deep neural networks) in various artificial intelligence applications, recently, ensemble learning based on deep neural networks (ensemble deep learning) has shown significant performances in improving the generalization of learning system. However, since modern deep neural networks usually have millions to billions of parameters, the time and space overheads for training multiple base deep learners and testing with the ensemble deep learner are far greater than that of traditional ensemble learning. Though several algorithms of fast ensemble deep learning have been proposed to promote the deployment of ensemble deep learning in some applications, further advances still need to be made for many applications in specific fields, where the developing time and computing resources are usually restricted or the data to be processed is of large dimensionality. An urgent problem needs to be solved is how to take the significant advantages of ensemble deep learning while reduce the required expenses so that many more applications in specific fields can benefit from it. For the alleviation of this problem, it is essential to know about how ensemble learning has developed under the era of deep learning. Thus, in this article, we present fundamental discussions focusing on data analyses of published works, methodologies, recent advances and unattainability of traditional ensemble learning and ensemble deep learning. We hope this article will be helpful to realize the intrinsic problems and technical challenges faced by future developments of ensemble learning under the era of deep learning.

cs.LG↗

arXiv2022

StackVAE-G: An efficient and interpretable model for time series anomaly detection

Recent studies have shown that autoencoder-based models can achieve superior performance on anomaly detection tasks due to their excellent ability to fit complex data in an unsupervised manner. In this work, we propose a novel autoencoder-based model, named StackVAE-G that can significantly bring the efficiency and interpretability to multivariate time series anomaly detection. Specifically, we utilize the similarities across the time series channels by the stacking block-wise reconstruction with a weight-sharing scheme to reduce the size of learned models and also relieve the overfitting to unknown noises in the training data. We also leverage a graph learning module to learn a sparse adjacency matrix to explicitly capture the stable interrelation structure among multiple time series channels for the interpretable pattern reconstruction of interrelated channels. Combining these two modules, we introduce the stacking block-wise VAE (variational autoencoder) with GNN (graph neural network) model for multivariate time series anomaly detection. We conduct extensive experiments on three commonly used public datasets, showing that our model achieves comparable (even better) performance with the state-of-the-art modelsand meanwhile requires much less computation and memory cost. Furthermore, we demonstrate that the adjacency matrix learned by our model accurately captures the interrelation among multiple channels, and can provide valuable information for failure diagnosis applications.

cs.LG↗

arXiv2022

Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk

Though deep reinforcement learning (DRL) has obtained substantial success, it may encounter catastrophic failures due to the intrinsic uncertainty of both transition and observation. Most of the existing methods for safe reinforcement learning can only handle transition disturbance or observation disturbance since these two kinds of disturbance affect different parts of the agent; besides, the popular worst-case return may lead to overly pessimistic policies. To address these issues, we first theoretically prove that the performance degradation under transition disturbance and observation disturbance depends on a novel metric of Value Function Range (VFR), which corresponds to the gap in the value function between the best state and the worst state. Based on the analysis, we adopt conditional value-at-risk (CVaR) as an assessment of risk and propose a novel reinforcement learning algorithm of CVaR-Proximal-Policy-Optimization (CPPO) which formalizes the risk-sensitive constrained optimization problem by keeping its CVaR under a given threshold. Experimental results show that CPPO achieves a higher cumulative reward and is more robust against both observation and transition disturbances on a series of continuous control tasks in MuJoCo.

cs.LG↗

arXiv2022

High Speed Rotation Estimation with Dynamic Vision Sensors

Rotational speed is one of the important metrics to be measured for calibrating the electric motors in manufacturing, monitoring engine during car repairing, faults detection on electrical appliance and etc. However, existing measurement techniques either require prohibitive hardware (e.g., high-speed camera) or are inconvenient to use in real-world application scenarios. In this paper, we propose, EV-Tach, an event-based tachometer via efficient dynamic vision sensing on mobile devices. EV-Tach is designed as a high-fidelity and convenient tachometer by introducing dynamic vision sensor as a new sensing modality to capture the high-speed rotation precisely under various real-world scenarios. By designing a series of signal processing algorithms bespoke for dynamic vision sensing on mobile devices, EV-Tach is able to extract the rotational speed accurately from the event stream produced by dynamic vision sensing on rotary targets. According to our extensive evaluations, the Relative Mean Absolute Error (RMAE) of EV-Tach is as low as 0.03% which is comparable to the state-of-the-art laser tachometer under fixed measurement mode. Moreover, EV-Tach is robust to subtle movement of user's hand, therefore, can be used as a handheld device, where the laser tachometer fails to produce reasonable results.

cs.CV↗

arXiv2022

A Comparative Study on Application of Class-Imbalance Learning for Severity Prediction of Adverse Events Following Immunization

In collaboration with the Liaoning CDC, China, we propose a prediction system to predict the subsequent hospitalization of children with adverse reactions based on data on adverse events following immunization. We extracted multiple features from the data, and selected "hospitalization or not" as the target for classification. Since the data are imbalanced, we used various class-imbalance learning methods for training and improved the RUSBoost algorithm. Experimental results show that the improved RUSBoost has the highest Area Under the ROC Curve on the target among these algorithms. Additionally, we compared these class-imbalance learning methods with some common machine learning algorithms. We combined the improved RUSBoost with dynamic web resource development techniques to build an evaluation system with information entry and vaccination response prediction capabilities for relevant medical practitioners.

cs.LG↗

arXiv2022

Multi-Domain Virtual Network Embedding Algorithm based on Horizontal Federated Learning

Network Virtualization (NV) is an emerging network dynamic planning technique to overcome network rigidity. As its necessary challenge, Virtual Network Embedding (VNE) enhances the scalability and flexibility of the network by decoupling the resources and services of the underlying physical network. For the future multi-domain physical network modeling with the characteristics of dynamics, heterogeneity, privacy, and real-time, the existing related works perform satisfactorily. Federated learning (FL) jointly optimizes the network by sharing parameters among multiple parties and is widely employed in disputes over data privacy and data silos. Aiming at the NV challenge of multi-domain physical networks, this work is the first to propose using FL to model VNE, and presents a VNE architecture based on Horizontal Federated Learning (HFL) (HFL-VNE). Specifically, combined with the distributed training paradigm of FL, we deploy local servers in each physical domain, which can effectively focus on local features and reduce resource fragmentation. A global server is deployed to aggregate and share training parameters, which enhances local data privacy and significantly improves learning efficiency. Furthermore, we deploy the Deep Reinforcement Learning (DRL) model in each server to dynamically adjust and optimize the resource allocation of the multi-domain physical network. In DRL-assisted FL, HFL-VNE jointly optimizes decision-making through specific local and federated reward mechanisms and loss functions. Finally, the superiority of HFL-VNE is proved by combining simulation experiments and comparing it with related works.

cs.NI↗

arXiv2022

Observation of fractal topological states in acoustic metamaterials

Topological phases of matter have been extensively investigated in solid state materials and classical wave systems with integer dimensions. However, topological states in non-integer dimensions remain largely unexplored. Fractals, being nearly the same at different scales, are one of the intriguing complex geometries with non-integer dimensions. Here, we demonstrate acoustic Sierpiński fractal topological insulators with unconventional higher-order topological phenomena via consistent theory and experiments. We discover abundant topological edge and corner states emerging in our acoustic systems due to the rich edge and corner boundaries inside the fractals. Interestingly, the numbers of the edge and corner states scale the same as the bulk states with the system size and the exponents coincide with the Hausdorff fractal dimension of the Sierpiński carpet. Furthermore, the emergent corner states exhibit unconventional spectrum and wave patterns. Our study opens a pathway toward topological states in fractal geometries.

cond-mat.mtrl-sci↗

arXiv2022

High-quality grand unified theories with three generations

We extend the unitary groups beyond the ${\rm SU}(5)$ and ${\rm SU}(6)$ to look for possible grand unified theories that give rise to three-generational Standard Model fermions without the simple repetition. By demanding asymptotic free theories at short distances, we find gauge groups of ${\rm SU}(7)$, ${\rm SU}(8)$ and ${\rm SU}(9)$ together with their anomaly-free irreducible representations are such candidates. Two additional gauge groups of ${\rm SU}(10)$ and ${\rm SU}(11)$ can also achieve the generational structure without asymptotic freedom. We also find these models can solve the Peccei-Quinn (PQ) quality problem which is intrinsic in the axion models, with the leading PQ-breaking operators determined from the symmetry requirement.

hep-ph↗

arXiv2021

Axion model with the ${\rm SU}(6)$ unification

We propose an ${\rm SU}(6)$ unified theory that solves the strong ${\it CP}$ problem with a high-quality axion. This is achieved by an automatic global Peccei-Quinn ${\rm U}(1)_{\rm PQ}$ symmetry and the gauged discrete $\mathbb{Z}_{4{\cal R}}$ symmetry. With the axion mass predictions of $m_a \sim {\cal O}(10^{-3} ) - {\cal O}(0.1) \,{\rm eV}$, as well as a universal axion-photon coupling in the unification models, the QCD axion can be probed in the upcoming experiments of IAXO. An intermediate gauge symmetry breaking scale characterized by the axion decay constant is obtained by the Peccei-Quinn quality argument, which is likely to achieve a successful leptogenesis through the type-I seesaw mechanism. The Higgs sector at the electroweak scale is a type-II two-Higgs-doublet model. The gauge coupling unification is possible with the supersymmetric extension.

hep-ph↗