arXiv subjects

Ying Zhang

Publications and source records attributed to Ying Zhang.

At least 361 records · Page 20Linked to original sources

arXiv2023

Non-asymptotic estimates for TUSLA algorithm for non-convex learning with applications to neural networks with ReLU activation function

We consider non-convex stochastic optimization problems where the objective functions have super-linearly growing and discontinuous stochastic gradients. In such a setting, we provide a non-asymptotic analysis for the tamed unadjusted stochastic Langevin algorithm (TUSLA) introduced in Lovas et al. (2020). In particular, we establish non-asymptotic error bounds for the TUSLA algorithm in Wasserstein-1 and Wasserstein-2 distances. The latter result enables us to further derive non-asymptotic estimates for the expected excess risk. To illustrate the applicability of the main results, we consider an example from transfer learning with ReLU neural networks, which represents a key paradigm in machine learning. Numerical experiments are presented for the aforementioned example which support our theoretical findings. Hence, in this setting, we demonstrate both theoretically and numerically that the TUSLA algorithm can solve the optimization problem involving neural networks with ReLU activation function. Besides, we provide simulation results for synthetic examples where popular algorithms, e.g. ADAM, AMSGrad, RMSProp, and (vanilla) stochastic gradient descent (SGD) algorithm, may fail to find the minimizer of the objective functions due to the super-linear growth and the discontinuity of the corresponding stochastic gradient, while the TUSLA algorithm converges rapidly to the optimal solution. Moreover, we provide an empirical comparison of the performance of TUSLA with popular stochastic optimizers on real-world datasets, as well as investigate the effect of the key hyperparameters of TUSLA on its performance.

math.OC↗

arXiv2023

Bi-AM-RRT*: A Fast and Efficient Sampling-Based Motion Planning Algorithm in Dynamic Environments

The efficiency of sampling-based motion planning brings wide application in autonomous mobile robots. The conventional rapidly exploring random tree (RRT) algorithm and its variants have gained significant successes, but there are still challenges for the optimal motion planning of mobile robots in dynamic environments. In this paper, based on Bidirectional RRT and the use of an assisting metric (AM), we propose a novel motion planning algorithm, namely Bi-AM-RRT*. Different from the existing RRT-based methods, the AM is introduced in this paper to optimize the performance of robot motion planning in dynamic environments with obstacles. On this basis, the bidirectional search sampling strategy is employed to reduce the search time. Further, we present a new rewiring method to shorten path lengths. The effectiveness and efficiency of the proposed Bi-AM-RRT* are proved through comparative experiments in different environments. Experimental results show that the Bi-AM-RRT* algorithm can achieve better performance in terms of path length and search time, and always finds near-optimal paths with the shortest search time when the diffusion metric is used as the AM.

cs.RO↗

arXiv2023

Disco Intelligent Reflecting Surfaces: Active Channel Aging for Fully-Passive Jamming Attacks

Due to the open communications environment in wireless channels, wireless networks are vulnerable to jamming attacks. However, existing approaches for jamming rely on knowledge of the legitimate users' (LUs') channels, extra jamming power, or both. To raise concerns about the potential threats posed by illegitimate intelligent reflecting surfaces (IRSs), we propose an alternative method to launch jamming attacks on LUs without either LU channel state information (CSI) or jamming power. The proposed approach employs an adversarial IRS with random phase shifts, referred to as a "disco" IRS (DIRS), that acts like a "disco ball" to actively age the LUs' channels. Such active channel aging (ACA) interference can be used to launch jamming attacks on multi-user multiple-input single-output (MU-MISO) systems. The proposed DIRS-based fully-passive jammer (FPJ) can jam LUs with no additional jamming power or knowledge of the LU CSI, and it can not be mitigated by classical anti-jamming approaches. A theoretical analysis of the proposed DIRS-based FPJ that provides an evaluation of the DIRS-based jamming attacks is derived. Based on this detailed theoretical analysis, some unique properties of the proposed DIRS-based FPJ can be obtained. Furthermore, a design example of the proposed DIRS-based FPJ based on one-bit quantization of the IRS phases is demonstrated to be sufficient for implementing the jamming attack. In addition, numerical results are provided to show the effectiveness of the derived theoretical analysis and the jamming impact of the proposed DIRS-based FPJ.

eess.SP↗

arXiv2023

CKM and PMNS mixing matrix from $SO(2)$ flavor symmetry

The relation between quark masses and CKM mixing is studied based on an approximate chiral $SO(2)_L\times SO(2)_R$ flavor symmetry of quark mass matrix. In mass hierarchy limit, the mass ratio effect to CKM mixing is suppressed, which separates mass hierarchy and quark flavor mixing into two independent problems. We show that CKM mixing is dominated by two left-handed $SO(2)_L^{u,d}$ symmetry while mass hierarchy only provides slight corrections. The same mixing structure is generalized to lepton sector with extended Dirac neutrinos. The common flavor mixing provides a novel comprehension on the relation between quark CKM mixing and lepton PMNS mixing.

hep-ph↗

arXiv2023

Multi-scale Attentive Image De-raining Networks via Neural Architecture Search

Multi-scale architectures and attention modules have shown effectiveness in many deep learning-based image de-raining methods. However, manually designing and integrating these two components into a neural network requires a bulk of labor and extensive expertise. In this article, a high-performance multi-scale attentive neural architecture search (MANAS) framework is technically developed for image deraining. The proposed method formulates a new multi-scale attention search space with multiple flexible modules that are favorite to the image de-raining task. Under the search space, multi-scale attentive cells are built, which are further used to construct a powerful image de-raining network. The internal multiscale attentive architecture of the de-raining network is searched automatically through a gradient-based search algorithm, which avoids the daunting procedure of the manual design to some extent. Moreover, in order to obtain a robust image de-raining model, a practical and effective multi-to-one training strategy is also presented to allow the de-raining network to get sufficient background information from multiple rainy images with the same background scene, and meanwhile, multiple loss functions including external loss, internal loss, architecture regularization loss, and model complexity loss are jointly optimized to achieve robust de-raining performance and controllable model complexity. Extensive experimental results on both synthetic and realistic rainy images, as well as the down-stream vision applications (i.e., objection detection and segmentation) consistently demonstrate the superiority of our proposed method. The code is publicly available at https://github.com/lcai-gz/MANAS.

cs.CV↗

arXiv2023

Limits of Predictability in Top-N Recommendation

Top-N recommendation aims to recommend each consumer a small set of N items from a large collection of items, and its accuracy is one of the most common indexes to evaluate the performance of a recommendation system. While a large number of algorithms are proposed to push the Top-N accuracy by learning the user preference from their history purchase data, a predictability question is naturally raised - whether there is an upper limit of such Top-N accuracy. This work investigates such predictability by studying the degree of regularity from a specific set of user behavior data. Quantifying the predictability of Top-N recommendations requires simultaneously quantifying the limits on the accuracy of the N behaviors with the highest probability. This greatly increases the difficulty of the problem. To achieve this, we firstly excavate the associations among N behaviors with the highest probability and describe the user behavior distribution based on the information theory. Then, we adopt the Fano inequality to scale and obtain the Top-N predictability. Extensive experiments are conducted on the real-world data where significant improvements are observed compared to the state-of-the-art methods. We have not only completed the predictability calculation for N targets but also obtained predictability that is much closer to the true value than existing methods. We expect our results to assist these research areas where the quantitative requirement of Top-N predictability is required.

cs.IR↗

arXiv2023

Plug-and-Play Regulators for Image-Text Matching

Exploiting fine-grained correspondence and visual-semantic alignments has shown great potential in image-text matching. Generally, recent approaches first employ a cross-modal attention unit to capture latent region-word interactions, and then integrate all the alignments to obtain the final similarity. However, most of them adopt one-time forward association or aggregation strategies with complex architectures or additional information, while ignoring the regulation ability of network feedback. In this paper, we develop two simple but quite effective regulators which efficiently encode the message output to automatically contextualize and aggregate cross-modal representations. Specifically, we propose (i) a Recurrent Correspondence Regulator (RCR) which facilitates the cross-modal attention unit progressively with adaptive attention factors to capture more flexible correspondence, and (ii) a Recurrent Aggregation Regulator (RAR) which adjusts the aggregation weights repeatedly to increasingly emphasize important alignments and dilute unimportant ones. Besides, it is interesting that RCR and RAR are plug-and-play: both of them can be incorporated into many frameworks based on cross-modal interaction to obtain significant benefits, and their cooperation achieves further improvements. Extensive experiments on MSCOCO and Flickr30K datasets validate that they can bring an impressive and consistent R@1 gain on multiple models, confirming the general effectiveness and generalization ability of the proposed methods. Code and pre-trained models are available at: https://github.com/Paranioar/RCAR.

cs.CV↗

arXiv2023

Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesis

Cross-speaker style transfer in speech synthesis aims at transferring a style from source speaker to synthesized speech of a target speaker's timbre. In most previous methods, the synthesized fine-grained prosody features often represent the source speaker's average style, similar to the one-to-many problem(i.e., multiple prosody variations correspond to the same text). In response to this problem, a strength-controlled semi-supervised style extractor is proposed to disentangle the style from content and timbre, improving the representation and interpretability of the global style embedding, which can alleviate the one-to-many mapping and data imbalance problems in prosody prediction. A hierarchical prosody predictor is proposed to improve prosody modeling. We find that better style transfer can be achieved by using the source speaker's prosody features that are easily predicted. Additionally, a speaker-transfer-wise cycle consistency loss is proposed to assist the model in learning unseen style-timbre combinations during the training phase. Experimental results show that the method outperforms the baseline. We provide a website with audio samples.

cs.SD↗

arXiv2023

Improving the quality of dental crown using a Transformer-based method

Designing a synthetic crown is a time-consuming, inconsistent, and labor-intensive process. In this work, we present a fully automatic method that not only learns human design dental crowns, but also improves the consistency, functionality, and esthetic of the crowns. Following success in point cloud completion using the transformer-based network, we tackle the problem of the crown generation as a point-cloud completion around a prepared tooth. To this end, we use a geometry-aware transformer to generate dental crowns. Our main contribution is to add a margin line information to the network, as the accuracy of generating a precise margin line directly,determines whether the designed crown and prepared tooth are closely matched to allowappropriateadhesion.Using our ground truth crown, we can extract the margin line as a spline and sample the spline into 1000 points. We feed the obtained margin line along with two neighbor teeth of the prepared tooth and three closest teeth in the opposing jaw. We also add the margin line points to our ground truth crown to increase the resolution at the margin line. Our experimental results show an improvement in the quality of the designed crown when considering the actual context composed of the prepared tooth along with the margin line compared with a crown generated in an empty space as was done by other studies in the literature.

cs.CV↗

arXiv2023

HGMatch: A Match-by-Hyperedge Approach for Subgraph Matching on Hypergraphs

Hypergraphs are generalisation of graphs in which a hyperedge can connect any number of vertices. It can describe n-ary relationships and high-order information among entities compared to conventional graphs. In this paper, we study the fundamental problem of subgraph matching on hypergraphs (i.e, subhypergraph matching). Existing methods directly extend subgraph matching algorithms to the case of hypergraphs. However, this approach delays hyperedge verification and underutilises the high-order information in hypergraphs, which leads to large search space and high enumeration cost. Furthermore, with the growing size of hypergraphs, it is becoming hard to compute subhypergraph matching sequentially. Thus, we propose an efficient and parallel subhypergraph matching system, HGMatch, to handle subhypergraph matching in massive hypergraphs. We proposes a novel match-by-hyperedge framework to utilise high-order information in hypergraphs and uses set operations for efficient candidates generation. Moreover, we develop an optimised parallel execution engine in HGMatch based on the dataflow model, which features a task-based scheduler and fine-grained dynamic work stealing to achieve bounded memory execution and better load balancing. Experimental evaluation on 10 real-world datasets shows that HGMatch outperforms the extended version of the state-of-the-art subgraph matching algorithms (CFL, DAF, CECI and RapidMatch) by orders of magnitude when using a single thread, and achieves almost linear scalability when the number of threads increases.

cs.DB↗

arXiv2023

The Minimal Flavor Structure of Quarks and Leptons

A flavor structure with minimal parameters is proposed to address the fermion mass hierarchy and flavor mixing for quarks and leptons. Yukawa interaction is reconstructed in a new basis to show a homological flat structure for up-type quarks, down-type quarks, charged leptons and Dirac neutrinos. A $SO(2)_{LR}^f$ flavor symmetry is found from the hierarchy masses of quarks and leptons, which dominated CKM mixing for quarks and PMNS for leptons. Since the minimal flavor structure successfully addresses CKM and PMNS even in the mass hierarchy limit, mass hierarchy and flavor mixing are two independent questions. As a prediction, a sum rule on the mixing angles and CP violation phase is suggested, which explains the smallness of $s_{13}$ as a natural result of the mass hierarchy. Generalizing the flat structure to quarks and leptons, a unified Yukawa interaction is achieved for all fermions with only a single coupling.

hep-ph↗

arXiv2023

SF-SGL: Solver-Free Spectral Graph Learning from Linear Measurements

This work introduces a highly-scalable spectral graph densification framework (SGL) for learning resistor networks with linear measurements, such as node voltages and currents. We show that the proposed graph learning approach is equivalent to solving the classical graphical Lasso problems with Laplacian-like precision matrices. We prove that given $O(\log N)$ pairs of voltage and current measurements, it is possible to recover sparse $N$-node resistor networks that can well preserve the effective resistance distances on the original graph. In addition, the learned graphs also preserve the structural (spectral) properties of the original graph, which can potentially be leveraged in many circuit design and optimization tasks. To achieve more scalable performance, we also introduce a solver-free method (SF-SGL) that exploits multilevel spectral approximation of the graphs and allows for a scalable and flexible decomposition of the entire graph spectrum (to be learned) into multiple different eigenvalue clusters (frequency bands). Such a solver-free approach allows us to more efficiently identify the most spectrally-critical edges for reducing various ranges of spectral embedding distortions. Through extensive experiments for a variety of real-world test cases, we show that the proposed approach is highly scalable for learning sparse resistor networks without sacrificing solution quality. We also introduce a data-driven EDA algorithm for vectorless power/thermal integrity verifications to allow estimating worst-case voltage/temperature (gradient) distributions across the entire chip by leveraging a few voltage/temperature measurements.

cs.LG↗

arXiv2023

Audio2Gestures: Generating Diverse Gestures from Audio

People may perform diverse gestures affected by various mental and physical factors when speaking the same sentences. This inherent one-to-many relationship makes co-speech gesture generation from audio particularly challenging. Conventional CNNs/RNNs assume one-to-one mapping, and thus tend to predict the average of all possible target motions, easily resulting in plain/boring motions during inference. So we propose to explicitly model the one-to-many audio-to-motion mapping by splitting the cross-modal latent code into shared code and motion-specific code. The shared code is expected to be responsible for the motion component that is more correlated to the audio while the motion-specific code is expected to capture diverse motion information that is more independent of the audio. However, splitting the latent code into two parts poses extra training difficulties. Several crucial training losses/strategies, including relaxed motion loss, bicycle constraint, and diversity loss, are designed to better train the VAE. Experiments on both 3D and 2D motion datasets verify that our method generates more realistic and diverse motions than previous state-of-the-art methods, quantitatively and qualitatively. Besides, our formulation is compatible with discrete cosine transformation (DCT) modeling and other popular backbones (\textit{i.e.} RNN, Transformer). As for motion losses and quantitative motion evaluation, we find structured losses/metrics (\textit{e.g.} STFT) that consider temporal and/or spatial context complement the most commonly used point-wise losses (\textit{e.g.} PCK), resulting in better motion dynamics and more nuanced motion details. Finally, we demonstrate that our method can be readily used to generate motion sequences with user-specified motion clips on the timeline.

cs.CV↗

arXiv2023

Illegal Intelligent Reflecting Surface Based Active Channel Aging: When Jammer Can Attack Without Power and CSI

Illegal intelligent reflecting surfaces (I-IRSs), i.e., the illegal deployment and utilization of IRSs, impose serious harmful impacts on wireless networks. The existing I-IRS-based illegal jammer (IJ) requires channel state information (CSI) or extra power or both, and therefore, the I-IRS-based IJ seems to be difficult to implement in practical wireless networks. To raise concerns about significant potential threats posed by I-IRSs, we propose an alternative method to jam legitimate users (LUs) without relying on the CSI. By using an I-IRS to actively change wireless channels, the orthogonality of multi-user beamforming vectors and the co-user channels is destroyed, and significant inter-user interference is then caused, which is referred to as active channel aging. Such a fully-passive jammer (FPJ) can launch jamming attacks on multi-user multiple-input single-output (MU-MISO) systems via inter-user interference caused by active channel aging, where the IJ requires no additional transmit power and instantaneous CSI. The simulation results show the effectiveness of the proposed FPJ scheme. Moreover, we also investigate how the transmit power and the number of quantization phase shift bits influence the jamming performance.

cs.IT↗

arXiv2022

GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records

There is an increasing interest in developing artificial intelligence (AI) systems to process and interpret electronic health records (EHRs). Natural language processing (NLP) powered by pretrained language models is the key technology for medical AI systems utilizing clinical narratives. However, there are few clinical language models, the largest of which trained in the clinical domain is comparatively small at 110 million parameters (compared with billions of parameters in the general domain). It is not clear how large clinical language models with billions of parameters can help medical AI systems utilize unstructured EHRs. In this study, we develop from scratch a large clinical language model - GatorTron - using >90 billion words of text (including >82 billion words of de-identified clinical text) and systematically evaluate it on 5 clinical NLP tasks including clinical concept extraction, medical relation extraction, semantic textual similarity, natural language inference (NLI), and medical question answering (MQA). We examine how (1) scaling up the number of parameters and (2) scaling up the size of the training data could benefit these NLP tasks. GatorTron models scale up the clinical language model from 110 million to 8.9 billion parameters and improve 5 clinical NLP tasks (e.g., 9.6% and 9.5% improvement in accuracy for NLI and MQA), which can be applied to medical AI systems to improve healthcare delivery. The GatorTron models are publicly available at: https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/models/gatortron_og.

cs.CL↗

arXiv2022

BadPrompt: Backdoor Attacks on Continuous Prompts

The prompt-based learning paradigm has gained much research attention recently. It has achieved state-of-the-art performance on several NLP tasks, especially in the few-shot scenarios. While steering the downstream tasks, few works have been reported to investigate the security problems of the prompt-based models. In this paper, we conduct the first study on the vulnerability of the continuous prompt learning algorithm to backdoor attacks. We observe that the few-shot scenarios have posed a great challenge to backdoor attacks on the prompt-based models, limiting the usability of existing NLP backdoor methods. To address this challenge, we propose BadPrompt, a lightweight and task-adaptive algorithm, to backdoor attack continuous prompts. Specially, BadPrompt first generates candidate triggers which are indicative for predicting the targeted label and dissimilar to the samples of the non-targeted labels. Then, it automatically selects the most effective and invisible trigger for each sample with an adaptive trigger optimization algorithm. We evaluate the performance of BadPrompt on five datasets and two continuous prompt models. The results exhibit the abilities of BadPrompt to effectively attack continuous prompts while maintaining high performance on the clean test sets, outperforming the baseline models by a large margin. The source code of BadPrompt is publicly available at https://github.com/papersPapers/BadPrompt.

cs.CL↗

arXiv2022

Joint Secure Communication and Radar Beamforming: A Secrecy-Estimation Rate-Based Design

This paper considers transmit beamforming in dual-function radar-communication (DFRC) system, where a DFRC transmitter simultaneously communicates with a communication user and detects a malicious target with the same waveform. Since the waveform is embedded with information, the information is risked to be intercepted by the target. To address this problem, physical-layer security technique is exploited. By using secrecy rate and estimation rate as performance measure for communication and radar, respectively, three secrecy rate maximization (SRM) problems are formulated, including the SRM with and without artificial noise (AN), and robust SRM. For the SRM beamforming, we prove that the optimal beamformer can be computed in closed form. For the AN-aided SRM, by leveraging alternating optimization similar closed-form solution is obtained for the beamformer and the AN covariance matrix. Finally, the imperfect CSI of the target is also considered under the premise of a moment-based random phase-error model on the direction of arrival at the target. Simulation results demonstrate the efficacy and robustness of the proposed designs.

eess.SP↗

arXiv2022

Efficiently Answering Quality Constrained Shortest Distance Queries in Large Graphs

The shortest-path distance is a fundamental concept in graph analytics and has been extensively studied in the literature. In many real-world applications, quality constraints are naturally associated with edges in the graphs and finding the shortest distance between two vertices $s$ and $t$ along only valid edges (i.e., edges that satisfy a given quality constraint) is also critical. In this paper, we investigate this novel and important problem of quality constraint shortest distance queries. We propose an efficient index structure based on 2-hop labeling approaches. Supported by a path dominance relationship incorporating both quality and length information, we demonstrate the minimal property of the new index. An efficient query processing algorithm is also developed. Extensive experimental studies over real-life datasets demonstrates efficiency and effectiveness of our techniques.

cs.DB↗