arXiv subjects

Yu Zhao

Publications and source records attributed to Yu Zhao.

At least 235 records · Page 13Linked to original sources

arXiv2022

DinoDroid: Testing Android Apps Using Deep Q-Networks

The large demand of mobile devices creates significant concerns about the quality of mobile applications (apps). Developers need to guarantee the quality of mobile apps before it is released to the market. There have been many approaches using different strategies to test the GUI of mobile apps. However, they still need improvement due to their limited effectiveness. In this paper, we propose DinoDroid, an approach based on deep Q-networks to automate testing of Android apps. DinoDroid learns a behavior model from a set of existing apps and the learned model can be used to explore and generate tests for new apps. DinoDroid is able to capture the fine-grained details of GUI events (e.g., the content of GUI widgets) and use them as features that are fed into deep neural network, which acts as the agent to guide app exploration. DinoDroid automatically adapts the learned model during the exploration without the need of any modeling strategies or pre-defined rules. We conduct experiments on 64 open-source Android apps. The results showed that DinoDroid outperforms existing Android testing tools in terms of code coverage and bug detection.

cs.SE↗

arXiv2022

Overcoming Language Priors in Visual Question Answering via Distinguishing Superficially Similar Instances

Despite the great progress of Visual Question Answering (VQA), current VQA models heavily rely on the superficial correlation between the question type and its corresponding frequent answers (i.e., language priors) to make predictions, without really understanding the input. In this work, we define the training instances with the same question type but different answers as \textit{superficially similar instances}, and attribute the language priors to the confusion of VQA model on such instances. To solve this problem, we propose a novel training framework that explicitly encourages the VQA model to distinguish between the superficially similar instances. Specifically, for each training instance, we first construct a set that contains its superficially similar counterparts. Then we exploit the proposed distinguishing module to increase the distance between the instance and its counterparts in the answer space. In this way, the VQA model is forced to further focus on the other parts of the input beyond the question type, which helps to overcome the language priors. Experimental results show that our method achieves the state-of-the-art performance on VQA-CP v2. Codes are available at \href{https://github.com/wyk-nku/Distinguishing-VQA.git}{Distinguishing-VQA}.

cs.CL↗

arXiv2022

Shuffle Instances-based Vision Transformer for Pancreatic Cancer ROSE Image Classification

The rapid on-site evaluation (ROSE) technique can signifi-cantly accelerate the diagnosis of pancreatic cancer by im-mediately analyzing the fast-stained cytopathological images. Computer-aided diagnosis (CAD) can potentially address the shortage of pathologists in ROSE. However, the cancerous patterns vary significantly between different samples, making the CAD task extremely challenging. Besides, the ROSE images have complicated perturbations regarding color distribution, brightness, and contrast due to different staining qualities and various acquisition device types. To address these challenges, we proposed a shuffle instances-based Vision Transformer (SI-ViT) approach, which can reduce the perturbations and enhance the modeling among the instances. With the regrouped bags of shuffle instances and their bag-level soft labels, the approach utilizes a regression head to make the model focus on the cells rather than various perturbations. Simultaneously, combined with a classification head, the model can effectively identify the general distributive patterns among different instances. The results demonstrate significant improvements in the classification accuracy with more accurate attention regions, indicating that the diverse patterns of ROSE images are effectively extracted, and the complicated perturbations are significantly reduced. It also suggests that the SI-ViT has excellent potential in analyzing cytopathological images. The code and experimental results are available at https://github.com/sagizty/MIL-SI.

eess.IV↗

arXiv2022

Asynchronous Federated Learning Based Mobility-aware Caching in Vehicular Edge Computing

Vehicular edge computing (VEC) is a promising technology to support real-time applications through caching the contents in the roadside units (RSUs), thus vehicles can fetch the contents requested by vehicular users (VUs) from the RSU within short time. The capacity of the RSU is limited and the contents requested by VUs change frequently due to the high-mobility characteristics of vehicles, thus it is essential to predict the most popular contents and cache them in the RSU in advance. The RSU can train model based on the VUs' data to effectively predict the popular contents. However, VUs are often reluctant to share their data with others due to the personal privacy. Federated learning (FL) allows each vehicle to train the local model based on VUs' data, and upload the local model to the RSU instead of data to update the global model, and thus VUs' privacy information can be protected. The traditional synchronous FL must wait all vehicles to complete training and upload their local models for global model updating, which would cause a long time to train global model. The asynchronous FL updates the global model in time once a vehicle's local model is received. However, the vehicles with different staying time have different impacts to achieve the accurate global model. In this paper, we consider the vehicle mobility and propose an Asynchronous FL based Mobility-aware Edge Caching (AFMC) scheme to obtain an accurate global model, and then propose an algorithm to predict the popular contents based on the global model. Experimental results show that AFMC outperforms other baseline caching schemes.

cs.DC↗

arXiv2022

Time-Dependent Performance Modeling for Platooning Communications at Intersection

With the development of internet of vehicles, platooning strategy has been widely studied as the potential approach to ensure the safety of autonomous driving. Vehicles in the form of platoon adopt 802.11p to exchange messages through vehicle to vehicle (V2V) communications. When multiple platoons arrive at an intersection, the leader vehicle of each platoon adjusts its movement characteristics to ensure that it can cross the intersection and thus the following vehicles have to adjust their movement characteristics accordingly. In this case, the time-varying connectivity among vehicles leads to the significant non-stationary performance change in platooning communications, which may incur safety issues. In this paper, we construct the time-dependent model to evaluate the platooning communication performance at the intersection based on the initial movement characteristics. We first consider the movement behaviors of vehicles at the intersection including turning, accelerating, decelerating and stopping as well as the periodic change of traffic lights to construct movement model, and then establish a hearing network to reflect the time-varying connectivity among vehicles. Afterwards, we adopt the pointwise stationary fluid flow approximation (PSFFA) to model the non-stationary behavior of transmission queue. Then, we consider four access categories (ACs) and continuous backoff freezing of 802.11p to construct the models to describe the time-dependent access process of 802.11p. Finally, based on the time-dependent model, the packet transmission delay and packet delivery ratio are derived. The accuracy of our proposed model is verified by comparing the simulation results with analytical results.

eess.SP↗

arXiv2022

Mobility-Aware Cooperative Caching in Vehicular Edge Computing Based on Asynchronous Federated and Deep Reinforcement Learning

The vehicular edge computing (VEC) can cache contents in different RSUs at the network edge to support the real-time vehicular applications. In VEC, owing to the high-mobility characteristics of vehicles, it is necessary to cache the user data in advance and learn the most popular and interesting contents for vehicular users. Since user data usually contains privacy information, users are reluctant to share their data with others. To solve this problem, traditional federated learning (FL) needs to update the global model synchronously through aggregating all users' local models to protect users' privacy. However, vehicles may frequently drive out of the coverage area of the VEC before they achieve their local model trainings and thus the local models cannot be uploaded as expected, which would reduce the accuracy of the global model. In addition, the caching capacity of the local RSU is limited and the popular contents are diverse, thus the size of the predicted popular contents usually exceeds the cache capacity of the local RSU. Hence, the VEC should cache the predicted popular contents in different RSUs while considering the content transmission delay. In this paper, we consider the mobility of vehicles and propose a cooperative Caching scheme in the VEC based on Asynchronous Federated and deep Reinforcement learning (CAFR). We first consider the mobility of vehicles and propose an asynchronous FL algorithm to obtain an accurate global model, and then propose an algorithm to predict the popular contents based on the global model. In addition, we consider the mobility of vehicles and propose a deep reinforcement learning algorithm to obtain the optimal cooperative caching location for the predicted popular contents in order to optimize the content transmission delay. Extensive experimental results have demonstrated that the CAFR scheme outperforms other baseline caching schemes.

cs.DC↗

arXiv2022

Combining Intra-Risk and Contagion Risk for Enterprise Bankruptcy Prediction Using Graph Neural Networks

Predicting the bankruptcy risk of small and medium-sized enterprises (SMEs) is an important step for financial institutions when making decisions about loans. Existing studies in both finance and AI research fields, however, tend to only consider either the intra-risk or contagion risk of enterprises, ignoring their interactions and combinatorial effects. This study for the first time considers both types of risk and their joint effects in bankruptcy prediction. Specifically, we first propose an enterprise intra-risk encoder based on statistically significant enterprise risk indicators for its intra-risk learning. Then, we propose an enterprise contagion risk encoder based on enterprise relation information from an enterprise knowledge graph for its contagion risk embedding. In particular, the contagion risk encoder includes both the newly proposed Hyper-Graph Neural Networks and Heterogeneous Graph Neural Networks, which can model contagion risk in two different aspects, i.e. common risk factors based on hyperedges and direct diffusion risk from neighbors, respectively. To evaluate the model, we collect real-world multi-sources data on SMEs and build a novel benchmark dataset called SMEsD. We provide open access to the dataset, which is expected to further promote research on financial risk analysis. Experiments on SMEsD against twelve state-of-the-art baselines demonstrate the effectiveness of the proposed model for bankruptcy prediction.

q-fin.RM↗

arXiv2022

Fast Electromagnetic Validations of Large-Scale Digital Coding Metasurfaces Accelerated by Recurrence Rebuild and Retrieval Method

The recurrence rebuild and retrieval method (R3M) is proposed in this paper to accelerate the electromagnetic (EM) validations of large-scale digital coding metasurfaces (DCMs). R3M aims to accelerate the EM validations of DCMs with varied codebooks, which involves the analysis of a group of similar but not identical structures. The method transforms general DCMs to rigorously periodic arrays by replacing each coding unit with the macro unit, which comprises all possible coding states. The system matrix corresponding to the rigorously periodic array is globally shared for DCMs with arbitrary codebooks via implicit retrieval. The discrepancy of the interactions for edge and corner units are precluded by the basis extension of periodic boundaries. Moreover, the hierarchical pattern exploitation (HPE) algorithm is leveraged to efficiently assemble the system matrix for further acceleration. Due to the fully utilization of the rigid periodicity, the computational complexity of R3M-HPE is theoretically lower than that of $\mathcal{H}$-matrix within the same paradigm. Numerical results for two types of DCMs indicate that R3M-HPE is accurate in comparison with commercial software. Besides, R3M-HPE is also compatible with the preconditioning for efficient iterative solutions. The efficiency of R3M-HPE for DCMs outperforms the conventional fast algorithms in both the storage and CPU time cost.

eess.SP↗

arXiv2022

Multi-objective optimization of longitudinal injection based on a multi-frequency RF system for fourth-generation storage ring-based light sources

In the fourth-generation storage ring light sources (4GLSs), associated with the extremely strong nonlinearities inherent in the multi-bend achromat design, the dynamic acceptance is usually small and it is difficult to implement traditional off-axis local-bump injection. To release the requirement on dynamic acceptance, on-axis longitudinal injection schemes have been explored. In this paper, we present a multi-objective optimization of longitudinal injection with a multi-frequency RF system, based on the parameters of the Southern Advanced Photon Source, a 4GLS proposed in China. We show that by treating the optimal bunch lengthening condition as an optimizing objective rather than a condition that must be satisfied, a plethora of feasible candidate solutions can be found, showing different trade-offs among multi-objectives. From these candidate solutions, one can find an optimal RF parameter setting that is most adapted to a specific 4GLS physics design and the available technical level of injection kicker. Especially, it would be feasible to realize longitudinal injection within a static bucket enabled by a double-frequency RF system, suggesting an attractive longitudinal injection option for 4GLSs.

physics.acc-ph↗

arXiv2022

ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classification

Whole slide image (WSI) classification often relies on deep weakly supervised multiple instance learning (MIL) methods to handle gigapixel resolution images and slide-level labels. Yet the decent performance of deep learning comes from harnessing massive datasets and diverse samples, urging the need for efficient training pipelines for scaling to large datasets and data augmentation techniques for diversifying samples. However, current MIL-based WSI classification pipelines are memory-expensive and computation-inefficient since they usually assemble tens of thousands of patches as bags for computation. On the other hand, despite their popularity in other tasks, data augmentations are unexplored for WSI MIL frameworks. To address them, we propose ReMix, a general and efficient framework for MIL based WSI classification. It comprises two steps: reduce and mix. First, it reduces the number of instances in WSI bags by substituting instances with instance prototypes, i.e., patch cluster centroids. Then, we propose a ``Mix-the-bag'' augmentation that contains four online, stochastic and flexible latent space augmentations. It brings diverse and reliable class-identity-preserving semantic changes in the latent space while enforcing semantic-perturbation invariance. We evaluate ReMix on two public datasets with two state-of-the-art MIL methods. In our experiments, consistent improvements in precision, accuracy, and recall have been achieved but with orders of magnitude reduced training time and memory consumption, demonstrating ReMix's effectiveness and efficiency. Code is available.

cs.CV↗

arXiv2022

Medical Dialogue Response Generation with Pivotal Information Recalling

Medical dialogue generation is an important yet challenging task. Most previous works rely on the attention mechanism and large-scale pretrained language models. However, these methods often fail to acquire pivotal information from the long dialogue history to yield an accurate and informative response, due to the fact that the medical entities usually scatters throughout multiple utterances along with the complex relationships between them. To mitigate this problem, we propose a medical response generation model with Pivotal Information Recalling (MedPIR), which is built on two components, i.e., knowledge-aware dialogue graph encoder and recall-enhanced generator. The knowledge-aware dialogue graph encoder constructs a dialogue graph by exploiting the knowledge relationships between entities in the utterances, and encodes it with a graph attention network. Then, the recall-enhanced generator strengthens the usage of these pivotal information by generating a summary of the dialogue before producing the actual response. Experimental results on two large-scale medical dialogue datasets show that MedPIR outperforms the strong baselines in BLEU scores and medical entities F1 measure.

cs.AI↗

arXiv2022

MSDF: A General Open-Domain Multi-Skill Dialog Framework

Dialog systems have achieved significant progress and have been widely used in various scenarios. The previous researches mainly focused on designing dialog generation models in a single scenario, while comprehensive abilities are required to handle tasks under various scenarios in the real world. In this paper, we propose a general Multi-Skill Dialog Framework, namely MSDF, which can be applied in different dialog tasks (e.g. knowledge grounded dialog and persona based dialog). Specifically, we propose a transferable response generator pre-trained on diverse large-scale dialog corpora as the backbone of MSDF, consisting of BERT-based encoders and a GPT-based decoder. To select the response consistent with dialog history, we propose a consistency selector trained through negative sampling. Moreover, the flexible copy mechanism of external knowledge is also employed to enhance the utilization of multiform knowledge in various scenarios. We conduct experiments on knowledge grounded dialog, recommendation dialog, and persona based dialog tasks. The experimental results indicate that our MSDF outperforms the baseline models with a large margin. In the Multi-skill Dialog of 2021 Language and Intelligence Challenge, our general MSDF won the 3rd prize, which proves our MSDF is effective and competitive.

cs.AI↗

arXiv2022

Timing performance simulation for 3D 4H-SiC detector

To meet high radiation challenge for detectors in future high-energy physics, a novel 3D 4H-SiC detector was investigated. SiC detectors could potentially operate in radiation harsh and room temperature environment because of its high thermal conductivity and high atomic displacement threshold energy. 3D structure, which decouples thickness and distance between electrodes, further improves timing performance and radiation hardness of the detector. We developed a simulation software - RASER (RAdiation SEmiconductoR) to simulate the time resolution of planar and 3D 4H-SiC detectors with different parameters and structures, and the reliability of the software is verified by comparing time resolution results of simulation with data. The rough time resolution of 3D 4H-SiC detector was estimated, and the simulation parameters could be used as guideline to 3D 4H-SiC detector design and optimization.

physics.ins-det↗

arXiv2022

Learning Bi-typed Multi-relational Heterogeneous Graph via Dual Hierarchical Attention Networks

Bi-type multi-relational heterogeneous graph (BMHG) is one of the most common graphs in practice, for example, academic networks, e-commerce user behavior graph and enterprise knowledge graph. It is a critical and challenge problem on how to learn the numerical representation for each node to characterize subtle structures. However, most previous studies treat all node relations in BMHG as the same class of relation without distinguishing the different characteristics between the intra-class relations and inter-class relations of the bi-typed nodes, causing the loss of significant structure information. To address this issue, we propose a novel Dual Hierarchical Attention Networks (DHAN) based on the bi-typed multi-relational heterogeneous graphs to learn comprehensive node representations with the intra-class and inter-class attention-based encoder under a hierarchical mechanism. Specifically, the former encoder aggregates information from the same type of nodes, while the latter aggregates node representations from its different types of neighbors. Moreover, to sufficiently model node multi-relational information in BMHG, we adopt a newly proposed hierarchical mechanism. By doing so, the proposed dual hierarchical attention operations enable our model to fully capture the complex structures of the bi-typed multi-relational heterogeneous graphs. Experimental results on various tasks against the state-of-the-arts sufficiently confirm the capability of DHAN in learning node representations on the BMHGs.

cs.LG↗

arXiv2022

Stock Movement Prediction Based on Bi-typed Hybrid-relational Market Knowledge Graph via Dual Attention Networks

Stock Movement Prediction (SMP) aims at predicting listed companies' stock future price trend, which is a challenging task due to the volatile nature of financial markets. Recent financial studies show that the momentum spillover effect plays a significant role in stock fluctuation. However, previous studies typically only learn the simple connection information among related companies, which inevitably fail to model complex relations of listed companies in the real financial market. To address this issue, we first construct a more comprehensive Market Knowledge Graph (MKG) which contains bi-typed entities including listed companies and their associated executives, and hybrid-relations including the explicit relations and implicit relations. Afterward, we propose DanSmp, a novel Dual Attention Networks to learn the momentum spillover signals based upon the constructed MKG for stock prediction. The empirical experiments on our constructed datasets against nine SOTA baselines demonstrate that the proposed DanSmp is capable of improving stock prediction with the constructed MKG.

q-fin.ST↗

arXiv2022

Improving Human-Object Interaction Detection via Phrase Learning and Label Composition

Human-Object Interaction (HOI) detection is a fundamental task in high-level human-centric scene understanding. We propose PhraseHOI, containing a HOI branch and a novel phrase branch, to leverage language prior and improve relation expression. Specifically, the phrase branch is supervised by semantic embeddings, whose ground truths are automatically converted from the original HOI annotations without extra human efforts. Meanwhile, a novel label composition method is proposed to deal with the long-tailed problem in HOI, which composites novel phrase labels by semantic neighbors. Further, to optimize the phrase branch, a loss composed of a distilling loss and a balanced triplet loss is proposed. Extensive experiments are conducted to prove the effectiveness of the proposed PhraseHOI, which achieves significant improvement over the baseline and surpasses previous state-of-the-art methods on Full and NonRare on the challenging HICO-DET benchmark.

cs.CV↗

arXiv2022

Differentiable Channel Sparsity Search via Weight Sharing within Filters

In this paper, we propose the differentiable channel sparsity search (DCSS) for convolutional neural networks. Unlike traditional channel pruning algorithms which require users to manually set prune ratios for each convolutional layer, DCSS automatically searches the optimal combination of sparsities. Inspired by the differentiable architecture search (DARTS), we draw lessons from the continuous relaxation and leverage the gradient information to balance the computational cost and metrics. Since directly applying the scheme of DARTS causes shape mismatching and excessive memory consumption, we introduce a novel technique called weight sharing within filters. This technique elegantly eliminates the problem of shape mismatching with negligible additional resources. We conduct comprehensive experiments on not only image classification but also find-grained tasks including semantic segmentation and image super resolution to verify the effectiveness of DCSS. Compared with previous network pruning approaches, DCSS achieves state-of-the-art results for image classification. Experimental results of semantic segmentation and image super resolution indicate that task-specific search achieves better performance than transferring slim models, demonstrating the wide applicability and high efficiency of DCSS.

cs.CV↗

arXiv2022

On the equilibrium of the Poisson-Nernst-Planck-Bikermann model equipping with the steric and correlation effects

The Poisson-Nernst-Planck-Bikermann (PNPB) model, in which the ions and water molecules are treated as different species with non-uniform sizes and valences with interstitial voids, can describe the steric and correlation effects in ionic solution neglected by the Poisson-Nernst-Planck and Poisson-Boltzmann theories with point charge assumption. In the PNPB model, the electric potential is governed by the fourth-order Poisson-Bikermann (4PBik) equation instead of the Poisson equation so that it can describe the correlation effect. What's more, the steric potential is included in the ionic and water fluxes as well as the equilibrium Fermi-like distributions which characterizes the steric effect quantitatively. In this work, after doing a nondimensionalization step, we analyze the self-adjointness and the kernel of the fourth-order operator of the 4PBik equation. Also, we show the positivity of the void volume function and the convexity of the free energy. Following these properties, the well-posedness of the PNPB model in equilibrium is given. Furthermore, because the PNPB model has an energy dissipated structure, we adopt a finite volume scheme which preserves the energy dissipated property at the semi-discrete level. After that, various numerical investigations are given to show the parameter dependence of the steric effect to the steady state.

math-ph↗