检索结果-内蒙古大学图书馆

Enhancing Code Representation Learning for Code Search with Abstract Code Semantics

学校读者我要写书评

暂无评论

Enhancing Code Representation Learning for Code Search with ...

International Joint Conference on Neural Networks (IJCNN)

作者： Shaojie Zhang Yiwei Ding Enrui Hu Yue Yu Yu Zhang Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Peng Cheng Laboratory Shenzhen China Distributed and Parallel Software Lab Huawei Shenzhen China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Code representation learning is an important way to encode the semantics of source code through pre-training. The learned representation supports a variety of downstream tasks, such as natural language code search and code defect detection. Inspired by pre-trained models for natural language representation learning, existing approaches often treat the source code or its structural information (e.g., Abstract Syntax Tree or AST) as a plain token sequence. Unlike natural language, programming language has its unique code unit information (e.g., identifiers and expressions) and logic information (e.g., the functionality of a code snippet). To further explore those properties, we propose Abstract Code Embedding (AbCE), a self-supervised learning method that considers the abstract semantics of code logic. Instead of scattered tokens, AbCE treats an entire node or a subtree in an AST as a basic code unit during pre-training, which preserves the entirety of a coding unit. Moreover, AbCE learns the abstract semantics of AST nodes via a self-distillation way. Experimental results show that it achieves significant improvements over state-of-the-art baselines on code search tasks and comparable performance on code clone detection and defect detection tasks even without using contrastive learning or curriculum learning.

关键词： Representation learning Codes Source coding Semantics Natural languages Cloning Syntactics

PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-label and Gaussian Process Guidance

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Taicai Duan, Yue Li, Dong Qi, Lei Shi, Yinghuan Gao, Yang National Key Laboratory for Novel Software Technology Nanjing University China Huawei Noah’s Ark Lab China School of Computer Science and Engineering Southeast University China

Variational Autoencoder based Bayesian Optimization (VAE-BO) has demonstrated its excellent performance in addressing high-dimensional structured optimization problems. However, current mainstream methods overlook the potential of utilizing a pool of unlabeled data to construct the latent space, while only concentrating on designing sophisticated models to leverage the labeled data. Despite their effective usage of labeled data, these methods often require extra network structures, additional procedure, resulting in computational inefficiency. To address this issue, we propose a novel method to effectively utilize unlabeled data with the guidance of labeled data. Specifically, we tailor the pseudo-labeling technique from semi-supervised learning to explicitly reveal the relative magnitudes of optimization objective values hidden within the unlabeled data. Based on this technique, we assign appropriate training weights to unlabeled data to enhance the construction of a discriminative latent space. Furthermore, we treat the VAE encoder and the Gaussian Process (GP) in Bayesian optimization as a unified deep kernel learning process, allowing the direct utilization of labeled data, which we term as Gaussian Process guidance. This directly and effectively integrates the goal of improving GP accuracy into the VAE training, thereby guiding the construction of the latent space. The extensive experiments demonstrate that our proposed method outperforms existing VAE-BO algorithms in various optimization scenarios. Our code will be published at https://***/TaicaiChen/PG-LBO. Copyright © 2023, The Authors. All rights reserved.

关键词： Gaussian distribution

PS3: Precise Patch Presence Test based on Semantic Symbolic Signature

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhan, Qi Xia, Xin Hu, Xing Lo, David Li, Zhiyang Li, Shanping The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Software Engineering Application Technology Lab China Singapore Management University Singapore Zhejiang University Hangzhou China

During software development, vulnerabilities have posed a significant threat to users. Patches are the most effective way to combat vulnerabilities. In a large-scale software system, testing the presence of a security patch in every affected binary is crucial to ensure system security. Identifying whether a binary has been patched for a known vulnerability is challenging, as there may only be small differences between patched and vulnerable versions. Existing approaches mainly focus on detecting patches that are compiled in the same compiler options. However, it is common for developers to compile programs with very different compiler options in different situations, which causes inaccuracy for existing methods. In this paper, we propose a new approach named PS3, referring to precise patch presence test based on semantic-level symbolic signature. PS3 exploits symbolic emulation to extract signatures that are stable under different compiler options. Then PS3 can precisely test the presence of the patch by comparing the signatures between the reference and the target at semantic level. To evaluate the effectiveness of our approach, we constructed a dataset consisting of 3,631 (CVE, binary) pairs of 62 recent CVEs in four C/C++ projects. The experimental results show that PS3 achieves scores of 0.82, 0.97, and 0.89 in terms of precision, recall, and F1 score, respectively. PS3 outperforms the state-of-the-art baselines by improving 33% in terms of F1 score and remains stable in different compiler options. © 2023, CC BY.

关键词： software design

AdaRate: A rate-adaptive traffic measurement method in software defined networks

学校读者我要写书评

暂无评论

International Journal of Performability engineering 2017年第6期13卷 937-944页

作者： Tang, Jixing Zhang, Yue Li, Yan MoE Engineering Research Center for Software/Hardware Co-Design Technology and Application East China Normal University Shanghai200062 China Shanghai Key Lab for Trustworthy Computing East China Normal University Shanghai200062 China

Traffic measurement is the basis of analysis and prediction of network traffic. Its accuracy directly affects the reliability of upper applications. This paper proposes a rate-adaptive traffic measurement method called AdaRate. It adjusts the polling period according to fluctuations of flow rates which is calculated with a sliding window queue. We noticed that some fluctuations of flow rates may be dropped in AdaRate while the polling period is too long. Then we propose RAdaRate. It adjusts the polling period according to AdaRate or sets the polling period to minimum randomly. We compared the performance of AdaRate and RAdaRate with SWT in CeMon and Payless in Mininet when monitoring those VBR flows with frequent and large fluctuation. The results show that the accuracy of RAdaRate is the best while the overhead of AdaRate is the least. The overhead of AdaRate is 68.75% less than periodic polling. © 2017 Totem Publisher, Inc. All rights reserved.

关键词： software defined networking

An end-to-end foreground-aware network for person re-identification

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Yiheng Zhou, Wengang Liu, Jianzhuang Qi, Guojun Tian, Qi Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China Noah’s Ark Lab Huawei Technologies Company Limited Shenzhen518129 China Huawei Cloud EI Product Department Cloud & AI Huawei Technologies

Person re-identification is a crucial task of identifying pedestrians of interest across multiple surveillance camera views. For person re-identification, a pedestrian is usually represented with features extracted from a rectangular image region that inevitably contains the scene background, which incurs ambiguity to distinguish different pedestrians and degrades the accuracy. Thus, we propose an end-to-end foreground-aware network to discriminate against the foreground from the background by learning a soft mask for person re-identification. In our method, in addition to the pedestrian ID as supervision for the foreground, we introduce the camera ID of each pedestrian image for background modeling. The foreground branch and the background branch are optimized collaboratively. By presenting a target attention loss, the pedestrian features extracted from the foreground branch become more insensitive to backgrounds, which greatly reduces the negative impact of changing backgrounds on pedestrian matching across different camera views. Notably, in contrast to existing methods, our approach does not require an additional dataset to train a human landmark detector or a segmentation model for locating the background regions. The experimental results conducted on three challenging datasets, i.e., Market-1501, DukeMTMC-reID, and MSMT17, demonstrate the effectiveness of our approach. Copyright © 2019, The Authors. All rights reserved.

关键词： Cameras

Context Aware Telco Churn Prediction Powered By Temporal Feature engineering

学校读者我要写书评

暂无评论

Context Aware Telco Churn Prediction Powered By Temporal Fea...

IEEE Annual Conference on Pervasive Computing and Communications Workshops (PerCom)

作者： Ruirui Bai Weixiong Rao Mingxuan Yuan Jia Zeng Jianfeng Yan School of Computer Science and Technology Soochow University Suzhou China School of Software Engineering Tongji University Shanghai China Huawei Noah’s Ark Lab Hong Kong China

ISBN: (纸本)9781538632284

It is still challenging in telecommunication (Telco) industry to precisely predict those who will churn from the current Telco operator to another one in next month. State of art approaches suffer from the issue that the predicted churners might be those silent customers with trivial profits to Telco operators. Thus, it is quite necessary to focus on the churn prediction problem with respect to active customers, instead of silent ones. Thus, we propose 3 kinds of new features in order to capture the context-aware customer behaviour in terms of temporal features. Such features include long-range Feature, trend feature and regression-based feature for Telco churn prediction. After that, we employ an ensemble process on the base learners: Random Forst (RF), XGB and GBDT + SVM. Experimental results confirm that the prediction performance has been improved by using these new features. From millions of active customers, this system can provide a list of prepaid customers who are most likely to churn in the next month, having 0.69 precision for the top 25000 predicted churners in the list. At the same time, achieve 44.69% improvement when given 5 × 10 4 .

关键词： Feature extraction Predictive models Computational modeling Market research Data models Ground penetrating radar History

FDA3: Federated defense against adversarial attacks for cloud-based iiot applications

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Song, Yunfei Liu, Tian Wei, Tongquan Wang, Xiangfeng Tao, Zhe Chen, Mingsong MoE Engineering Research Center of Software Hardware Co-design Technology and Application East China Normal University Shanghai200062 China Shanghai Institute of Intelligent Science and Technology Tongji University Godel Lab Shanghai China

—Along with the proliferation of Artificial Intelligence (AI) and Internet of Things (IoT) techniques, various kinds of adversarial attacks are increasingly emerging to fool Deep Neural Networks (DNNs) used by Industrial IoT (IIoT) applications. Due to biased training data or vulnerable underlying models, imperceptible modifications on inputs made by adversarial attacks may result in devastating consequences. Although existing methods are promising in defending such malicious attacks, most of them can only deal with limited existing attack types, which makes the deployment of large-scale IIoT devices a great challenge. To address this problem, we present an effective federated defense approach named FDA3 that can aggregate defense knowledge against adversarial examples from different sources. Inspired by federated learning, our proposed cloud-based architecture enables the sharing of defense capabilities against different attacks among IIoT devices. Comprehensive experimental results show that the generated DNNs by our approach can not only resist more malicious attacks than existing attack-specific adversarial training methods, but also can prevent IIoT applications from new attacks. Copyright © 2020, The Authors. All rights reserved.

关键词： Network security

Towards Efficient Workflow Scheduling Over Yarn Cluster Using Deep Reinforcement Learning

学校读者我要写书评

暂无评论

Towards Efficient Workflow Scheduling Over Yarn Cluster Usin...

IEEE Conference on Global Communications (GLOBECOM)

作者： Jianguo Xue Ting Wang Puyu Cai MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Lab. of Trustworthy Computing East China Normal University China Department of Computer Science and Engineering Michigan State University USA

Hadoop Yarn is an open-source cluster manager responsible for resource management and job scheduling. However, data-driven applications are typically organized into workflows that consist of a series of jobs with dependencies. Yarn does not manage users' workflows and only considers the current job rather than the entire workflow when scheduling. In practice, multiple workflows share the same Yarn cluster and are pre-assigned separate Yarn resource queues to avoid mutual interference. However, this coarse-grained resource division can sometimes result in low resource utilization and increased pending time of jobs on the Yarn queue. For instance, one resource queue may have exhausted its quota while still having pending jobs, while other queues may have available resources but cannot begin executing any jobs due to unfulfilled data dependencies. To address this problem, we propose a deep reinforcement learning-based workflow scheduling scheme that takes into account job dependencies, job priorities, and dynamic resource usage. The proposed approach can intelligently identify and utilize free windows of different resource queues. Our simulation results demonstrate that the proposed DRL-based workflow scheduling scheme can significantly reduce the average job latency compared to existing approaches.

关键词：

Green Federated Learning over Cloud-RAN with Limited Fronthaul and Quantized Neural Networks

学校读者我要写书评

暂无评论

Green Federated Learning over Cloud-RAN with Limited Frontha...

Communications and Networking (MeditCom), IEEE International Mediterranean Conference on

作者： Jiali Wang Yijie Mao Ting Wang Yuanming Shi MoE Engineering Research Center of Software/Hardware Co-Design Technology and Application Shanghai Key Lab. of Trustworthy Computing East China Normal University China School of Information Science and Technology (SIST) ShanghaiTech University China

In this paper, we investigate a green federated learning (FL) framework over cloud radio access network (Cloud-RAN) system that comprises a server, multiple devices and remote radio heads (RRHs). Each device utilizes quantized neural networks (QNNs) and sends quantized model parameters to the server to save energy consumption via RRHs. The server aggregates all the signals to update the global model parameters and broadcasts the updated parameters to the selected devices. In this context, we propose an energy consumption model for the QNN training and communication model over Cloud-RAN. We develop an energy minimization problem based on the proposed energy model. We jointly design fronthaul rate allocation, device transmit power, and precision level of QNNs while ensuring target accuracy, transmit power budget and limited fronthaul capacity. Guided by the convergence analysis, we adopt alternative optimization method to solve the energy minimization problem. The simulation outcomes demonstrate that the FL framework suggested can considerably diminish energy usage in comparison to other traditional methods. This has immense potential in realizing a sustainable and eco-friendly FL over Cloud-RAN.

关键词：