arXiv subjects

Li Li

Publications and source records attributed to Li Li.

At least 451 records · Page 25Linked to original sources

arXiv2022

Federated Noisy Client Learning

Federated learning (FL) collaboratively trains a shared global model depending on multiple local clients, while keeping the training data decentralized in order to preserve data privacy. However, standard FL methods ignore the noisy client issue, which may harm the overall performance of the shared model. We first investigate critical issue caused by noisy clients in FL and quantify the negative impact of the noisy clients in terms of the representations learned by different layers. We have the following two key observations: (1) the noisy clients can severely impact the convergence and performance of the global model in FL, and (2) the noisy clients can induce greater bias in the deeper layers than the former layers of the global model. Based on the above observations, we propose Fed-NCL, a framework that conducts robust federated learning with noisy clients. Specifically, Fed-NCL first identifies the noisy clients through well estimating the data quality and model divergence. Then robust layer-wise aggregation is proposed to adaptively aggregate the local models of each client to deal with the data heterogeneity caused by the noisy clients. We further perform the label correction on the noisy clients to improve the generalization of the global model. Experimental results on various datasets demonstrate that our algorithm boosts the performances of different state-of-the-art systems with noisy clients. Our code is available on https://github.com/TKH666/Fed-NCL

cs.LG↗

arXiv2022

CLIP2GAN: Towards Bridging Text with the Latent Space of GANs

In this work, we are dedicated to text-guided image generation and propose a novel framework, i.e., CLIP2GAN, by leveraging CLIP model and StyleGAN. The key idea of our CLIP2GAN is to bridge the output feature embedding space of CLIP and the input latent space of StyleGAN, which is realized by introducing a mapping network. In the training stage, we encode an image with CLIP and map the output feature to a latent code, which is further used to reconstruct the image. In this way, the mapping network is optimized in a self-supervised learning way. In the inference stage, since CLIP can embed both image and text into a shared feature embedding space, we replace CLIP image encoder in the training architecture with CLIP text encoder, while keeping the following mapping network as well as StyleGAN model. As a result, we can flexibly input a text description to generate an image. Moreover, by simply adding mapped text features of an attribute to a mapped CLIP image feature, we can effectively edit the attribute to the image. Extensive experiments demonstrate the superior performance of our proposed CLIP2GAN compared to previous methods.

cs.CV↗

arXiv2022

Realigned Hardy's Paradox

Hardy's paradox provides an all-versus-nothing fashion to directly certify that quantum mechanics cannot be completely described by local realistic theory. However, when considering potential imperfections in experiments, like imperfect entanglement source and low detection efficiency, the original Hardy's paradox may induce a rather small Hardy violation and only be realized by expensive quantum systems. To overcome this problem, we propose a realigned Hardy's paradox. Compared with the original version of Hardy's paradox, the realigned Hardy's paradox can dramatically improve the Hardy violation. Then, we generalize the realigned Hardy's paradox to arbitrary even $n$ dichotomic measurements. For $n=2$ and $n=4$ cases, the realigned Hardy's paradox can achieve Hardy values $P(00|A_1B_1)$ approximate $0.4140$ and $0.7734$ respectively compared with $0.09$ of the original Hardy's paradox. Meanwhile, the structure of the realigned Hardy's paradox is simpler and more robust in the sense that there is only one Hardy condition rather than three conditions. One can anticipate that the realigned Hardy's paradox can tolerate more experimental imperfections and stimulate more fascinating quantum information applications.

quant-ph↗

arXiv2022

Optimised Bayesian system identification in quantum devices

Identifying and calibrating quantitative dynamical models for physical quantum systems is important for a variety of applications. Here we present a closed-loop Bayesian learning algorithm for estimating multiple unknown parameters in a dynamical model, using optimised experimental "probe" controls and measurement. The estimation algorithm is based on a Bayesian particle filter, and is designed to autonomously choose informationally-optimised probe experiments with which to compare to model predictions. We demonstrate the performance of the algorithm in both simulated calibration tasks and in an experimental single-qubit ion-trap system. Experimentally, we find that with 60x fewer samples, we exceed the precision of conventional calibration methods, delivering an approximately 93x improvement in efficiency (as quantified by the reduction of measurements required to achieve a target residual uncertainty and multiplied by the increase in accuracy). In simulated and experimental demonstrations, we see that successively longer pulses are selected as the posterior uncertainty iteratively decreases, leading to an exponential improvement in the accuracy of model parameters with the number of experimental queries.

quant-ph↗

arXiv2022

Music Similarity Calculation of Individual Instrumental Sounds Using Metric Learning

The criteria for measuring music similarity are important for developing a flexible music recommendation system. Some data-driven methods have been proposed to calculate music similarity from only music signals, such as metric learning based on a triplet loss using tag information on each musical piece. However, the resulting music similarity metric usually captures the entire piece of music, i.e., the mixing of various instrumental sound sources, limiting the capability of the music recommendation system, e.g., it is difficult to search for a musical piece containing similar drum sounds. Towards the development of a more flexible music recommendation system, we propose a music similarity calculation method that focuses on individual instrumental sound sources in a musical piece. By fully exploiting the potential of data-driven methods for our proposed method, we employ weakly supervised metric learning to individual instrumental sound source signals without using any tag information, where positive and negative samples in a triplet loss are defined by whether or not they are from the same musical piece. Furthermore, assuming that each instrumental sound source is not always available in practice, we also investigate the effects of using instrumental sound source separation to obtain each source in the proposed method. Experimental results have shown that (1) unique similarity metrics can be learned for individual instrumental sound sources, (2) similarity metrics learned using some instrumental sound sources are possible to lead to more accurate results than that learned using the entire musical piece, (3) the performance degraded when learning with the separated instrumental sounds, and (4) similarity metrics learned by the proposed method well produced results that correspond to perception by human senses.

cs.SD↗

arXiv2022

Automated Detection, Categorisation and Developers' Experience with the Violations of Honesty in Mobile Apps

Human values such as honesty, social responsibility, fairness, privacy, and the like are things considered important by individuals and society. Software systems, including mobile software applications (apps), may ignore or violate such values, leading to negative effects in various ways for individuals and society. While some works have investigated different aspects of human values in software engineering, this mixed-methods study focuses on honesty as a critical human value. In particular, we studied (i) how to detect honesty violations in mobile apps, (ii) the types of honesty violations in mobile apps, and (iii) the perspectives of app developers on these detected honesty violations. We first develop and evaluate 7 machine learning (ML) models to automatically detect violations of the value of honesty in app reviews from an end user perspective. The most promising was a Deep Neural Network model with F1 score of 0.921. We then conducted a manual analysis of 401 reviews containing honesty violations and characterised honest violations in mobile apps into 10 categories: unfair cancellation and refund policies; false advertisements; delusive subscriptions; cheating systems; inaccurate information; unfair fees; no service; deletion of reviews; impersonation; and fraudulent looking apps. A developer survey and interview study with mobile developers then identified 7 key causes behind honesty violations in mobile apps and 8 strategies to avoid or fix such violations. The findings of our developer study also articulate the negative consequences that honesty violations might bring for businesses, developers, and users. Finally, the app developers' feedback shows that our prototype ML-based models can have promising benefits in practice.

cs.SE↗

arXiv2022

The Best of Both Worlds: Combining Learned Embeddings with Engineered Features for Accurate Prediction of Correct Patches

A large body of the literature on automated program repair develops approaches where patches are automatically generated to be validated against an oracle (e.g., a test suite). Because such an oracle can be imperfect, the generated patches, although validated by the oracle, may actually be incorrect. Our empirical work investigates different representation learning approaches for code changes to derive embeddings that are amenable to similarity computations of patch correctness identification, and assess the possibility of accurate classification of correct patch by combining learned embeddings with engineered features. Experimental results demonstrate the potential of learned embeddings to empower Leopard (a patch correctness predicting framework implemented in this work) with learning algorithms in reasoning about patch correctness: a machine learning predictor with BERT transformer-based learned embeddings associated with XGBoost achieves an AUC value of about 0.803 in the prediction of patch correctness on a new dataset of 2,147 labeled patches that we collected for the experiments. Our investigations show that deep learned embeddings can lead to complementary/better performance when comparing against the state-of-the-art, PATCH-SIM, which relies on dynamic information. By combining deep learned embeddings and engineered features, Panther (the upgraded version of Leopard implemented in this work) outperforms Leopard with higher scores in terms of AUC, +Recall and -Recall, and can accurately identify more (in)correct patches that cannot be predicted by the classifiers only with learned embeddings or engineered features. Finally, we use an explainable ML technique, SHAP, to empirically interpret how the learned embeddings and engineered features are contributed to the patch correctness prediction.

cs.SE↗

arXiv2022

Coordinating CAV Swarms at Intersections with a Deep Learning Model

Connected and automated vehicles (CAVs) are viewed as a special kind of robots that have the potential to significantly improve the safety and efficiency of traffic. In contrast to many swarm robotics studies that are demonstrated in labs by employing a small number of robots, CAV studies aims to achieve cooperative driving of unceasing robot swarm flows. However, how to get the optimal passing order of such robot swarm flows even for a signal-free intersection is an NP-hard problem (specifically, enumerating based algorithm takes days to find the optimal solution to a 20-CAV scenario). Here, we introduce a novel cooperative driving algorithm (AlphaOrder) that combines offline deep learning and online tree searching to find a near-optimal passing order in real-time. AlphaOrder builds a pointer network model from solved scenarios and generates near-optimal passing orders instantaneously for new scenarios. Furthermore, our approach provides a general approach to managing preemptive resource sharing between swarm robotics (e.g., scheduling multiple automated guided vehicles (AGVs) and unmanned aerial vehicles (UAVs) at conflicting areas

cs.RO↗

arXiv2022

A generic framework for genuine multipartite entanglement detection

Design of detection strategies for multipartite entanglement stands as a central importance on our understanding of fundamental quantum mechanics and has had substantial impact on quantum information applications. However, accurate and robust detection approaches are severely hindered, particularly when the number of nodes grows rapidly like in a quantum network. Here we present an exquisite procedure that generates novel entanglement witness for arbitrary targeted state via a generic and operational framework. The framework enjoys a systematic and high-efficient character and allows to substantiate genuine multipartite entanglement for a variety of states that arise naturally in practical situations, and to dramatically outperform currently standard methods. With excellent noise tolerance, our framework should be broadly applicable to witness genuine multipartite entanglement in various practically scenarios, and to facilitate making the best use of entangled resources in the emerging area of quantum network.

quant-ph↗

arXiv2022

A First Look at CI/CD Adoptions in Open-Source Android Apps

Continuous Integration (CI) and Continuous Delivery (CD) have been demonstrated to be effective in facilitating software building, testing, and deployment. Many research studies have investigated and subsequently improved their working processes. Unfortunately, such research efforts have largely not touched on the usage of CI/CD in the development of Android apps. We fill this gap by conducting an exploratory study of CI/CD adoption in open-source Android apps. We start by collecting a set of 84,475 open-source Android apps from the most popular three online code hosting sites, namely Github, GitLab, and Bitbucket. We then look into those apps and find that (1) only around 10\% of apps have leveraged CI/CD services, i.e., the majority of open-source Android apps are developed without accessing CI/CD services, (2) a small number of apps (291) has even adopted multiple CI/CD services, (3) nearly half of the apps adopted CI/CD services have not really used them, and (4) CI/CD services are useful to improve the popularity of projects.

cs.SE↗

arXiv2022

Demystifying Hidden Sensitive Operations in Android apps

Security of Android devices is now paramount, given their wide adoption among consumers. As researchers develop tools for statically or dynamically detecting suspicious apps, malware writers regularly update their attack mechanisms to hide malicious behavior implementation. This poses two problems to current research techniques: static analysis approaches, given their over-approximations, can report an overwhelming number of false alarms, while dynamic approaches will miss those behaviors that are hidden through evasion techniques. We propose in this work a static approach specifically targeted at highlighting hidden sensitive operations, mainly sensitive data flows. The prototype version of HiSenDroid has been evaluated on a large-scale dataset of thousands of malware and goodware samples on which it successfully revealed anti-analysis code snippets aiming at evading detection by dynamic analysis. We further experimentally show that, with FlowDroid, some of the hidden sensitive behaviors would eventually lead to private data leaks. Those leaks would have been hard to spot either manually among the large number of false positives reported by the state of the art static analyzers, or by dynamic tools. Overall, by putting the light on hidden sensitive operations, HiSenDroid helps security analysts in validating potential sensitive data operations, which would be previously unnoticed.

cs.CR↗

arXiv2022

aiWave: Volumetric Image Compression with 3-D Trained Affine Wavelet-like Transform

Volumetric image compression has become an urgent task to effectively transmit and store images produced in biological research and clinical practice. At present, the most commonly used volumetric image compression methods are based on wavelet transform, such as JP3D. However, JP3D employs an ideal, separable, global, and fixed wavelet basis to convert input images from pixel domain to frequency domain, which seriously limits its performance. In this paper, we first design a 3-D trained wavelet-like transform to enable signal-dependent and non-separable transform. Then, an affine wavelet basis is introduced to capture the various local correlations in different regions of volumetric images. Furthermore, we embed the proposed wavelet-like transform to an end-to-end compression framework called aiWave to enable an adaptive compression scheme for various datasets. Last but not least, we introduce the weight sharing strategies of the affine wavelet-like transform according to the volumetric data characteristics in the axial direction to reduce the amount of parameters. The experimental results show that: 1) when cooperating our trained 3-D affine wavelet-like transform with a simple factorized entropy module, aiWave performs better than JP3D and is comparable in terms of encoding and decoding complexities; 2) when adding a context module to further remove signal redundancy, aiWave can achieve a much better performance than HEVC.

eess.IV↗

arXiv2022

On the ordering of the Markov numbers

The Markov numbers are the positive integers that appear in the solutions of the equation $x^2+y^2+z^2=3xyz$. These numbers are a classical subject in number theory and have important ramifications in hyperbolic geometry, algebraic geometry and combinatorics. It is known that the Markov numbers can be labeled by the lattice points $(q,p)$ in the first quadrant and below the diagonal whose coordinates are coprime. In this paper, we consider the following question. Given two lattice points, can we say which of the associated Markov numbers is larger? A complete answer to this question would solve the uniqueness conjecture formulated by Frobenius in 1913. We give a partial answer in terms of the slope of the line segment that connects the two lattice points. We prove that the Markov number with the greater $x$-coordinate is larger than the other if the slope is at least $-\frac{8}{7}$ and that it is smaller than the other if the slope is at most $-\frac{5}{4}$. As a special case, namely when the slope is equal to 0 or 1, we obtain a proof of two conjectures from Aigner's book "Markov's theorem and 100 years of the uniqueness conjecture".

math.NT↗

arXiv2022

DeepMLE: A Robust Deep Maximum Likelihood Estimator for Two-view Structure from Motion

Two-view structure from motion (SfM) is the cornerstone of 3D reconstruction and visual SLAM (vSLAM). Many existing end-to-end learning-based methods usually formulate it as a brute regression problem. However, the inadequate utilization of traditional geometry model makes the model not robust in unseen environments. To improve the generalization capability and robustness of end-to-end two-view SfM network, we formulate the two-view SfM problem as a maximum likelihood estimation (MLE) and solve it with the proposed framework, denoted as DeepMLE. First, we propose to take the deep multi-scale correlation maps to depict the visual similarities of 2D image matches decided by ego-motion. In addition, in order to increase the robustness of our framework, we formulate the likelihood function of the correlations of 2D image matches as a Gaussian and Uniform mixture distribution which takes the uncertainty caused by illumination changes, image noise and moving objects into account. Meanwhile, an uncertainty prediction module is presented to predict the pixel-wise distribution parameters. Finally, we iteratively refine the depth and relative camera pose using the gradient-like information to maximize the likelihood function of the correlations. Extensive experimental results on several datasets prove that our method significantly outperforms the state-of-the-art end-to-end two-view SfM approaches in accuracy and generalization capability.

cs.CV↗

arXiv2022

A New Fuzzy $H_{\infty}$ Filter Design for Nonlinear Time-Delay Systems with Mismatched Premise Membership Functions

This paper is concerned with the fuzzy $H_{\infty}$ filter design issue for nonlinear systems with time-varying delay. To overcome the shortcomings of the conventional methods with matched preconditions, the fuzzy $H_{\infty}$ filter to be designed and the T-S fuzzy model are assumed to have different premise membership functions and number of rules, thus, greater design flexibility and robustness to uncertainty can be achieved. However, such design will also make the derived results conservative, to relax the result, a novel integral inequality which is tighter than the traditional inequalities derived from the Leibniz-Newton formula is applied, besides, a fuzzy Lypunov function and the information of the membership functions are also introduced. All the design methods are presented in LMI-based conditions. Finally, two numerical examples are given to prove the effectiveness and superiority of the proposed approach.

eess.SY↗

arXiv2022

Improved Fuzzy $H_{\infty}$ Filter Design Method for Nonlinear Systems with Time-Varing Delay

This paper investigates the fuzzy $H_{\infty}$ filter design issue for nonlinear systems with time-varying delay. In order to obtain less conservative fuzzy $H_{\infty}$ filter design method, a novel integral inequality is employed to replace the conventional Lebniz-Newton formula to analyze the stability conditions of the filtering error system. Besides, the information of the membership functions is introduced in the criterion to further relax the derived results. The proposed delay dependent filter design method is presented as LMI-based conditions, and corresponding definite expressions of fuzzy $H_{\infty}$ filter are given as well. Finally, a simulation example is provided to prove the effectiveness and superiority of the designed fuzzy $H_{\infty}$ filter.

eess.SY↗

arXiv2022

FastMVAE2: On improving and accelerating the fast variational autoencoder-based source separation algorithm for determined mixtures

This paper proposes a new source model and training scheme to improve the accuracy and speed of the multichannel variational autoencoder (MVAE) method. The MVAE method is a recently proposed powerful multichannel source separation method. It consists of pretraining a source model represented by a conditional VAE (CVAE) and then estimating separation matrices along with other unknown parameters so that the log-likelihood is non-decreasing given an observed mixture signal. Although the MVAE method has been shown to provide high source separation performance, one drawback is the computational cost of the backpropagation steps in the separation-matrix estimation algorithm. To overcome this drawback, a method called "FastMVAE" was subsequently proposed, which uses an auxiliary classifier VAE (ACVAE) to train the source model. By using the classifier and encoder trained in this way, the optimal parameters of the source model can be inferred efficiently, albeit approximately, in each step of the algorithm. However, the generalization capability of the trained ACVAE source model was not satisfactory, which led to poor performance in situations with unseen data. To improve the generalization capability, this paper proposes a new model architecture (called the "ChimeraACVAE" model) and a training scheme based on knowledge distillation. The experimental results revealed that the proposed source model trained with the proposed loss function achieved better source separation performance with less computation time than FastMVAE. We also confirmed that our methods were able to separate 18 sources with a reasonably good accuracy.

cs.SD↗

arXiv2022

Explainable AI for Android Malware Detection: Towards Understanding Why the Models Perform So Well?

Machine learning (ML)-based Android malware detection has been one of the most popular research topics in the mobile security community. An increasing number of research studies have demonstrated that machine learning is an effective and promising approach for malware detection, and some works have even claimed that their proposed models could achieve 99\% detection accuracy, leaving little room for further improvement. However, numerous prior studies have suggested that unrealistic experimental designs bring substantial biases, resulting in over-optimistic performance in malware detection. Unlike previous research that examined the detection performance of ML classifiers to locate the causes, this study employs Explainable AI (XAI) approaches to explore what ML-based models learned during the training process, inspecting and interpreting why ML-based malware classifiers perform so well under unrealistic experimental settings. We discover that temporal sample inconsistency in the training dataset brings over-optimistic classification performance (up to 99\% F1 score and accuracy). Importantly, our results indicate that ML models classify malware based on temporal differences between malware and benign, rather than the actual malicious behaviors. Our evaluation also confirms the fact that unrealistic experimental designs lead to not only unrealistic detection performance but also poor reliability, posing a significant obstacle to real-world applications. These findings suggest that XAI approaches should be used to help practitioners/researchers better understand how do AI/ML models (i.e., malware detection) work -- not just focusing on accuracy improvement.

cs.CR↗