检索结果-内蒙古大学图书馆

Scalable Optimal Margin Distribution Machine

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Yilin Cao, Nan Zhang, Teng Shi, Xuanhua Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

Optimal margin Distribution Machine (ODM) is a newly proposed statistical learning framework rooting in the latest margin theory, which demonstrates better generalization performance than the traditional large margin based counterparts. However, it suffers from the ubiquitous scalability problem regarding both computation time and memory storage as other kernel methods. This paper proposes a scalable ODM, which can achieve nearly ten times speedup compared to the original ODM training method. For nonlinear kernels, we put forward a novel distribution-aware partition method to make the local ODM trained on each partition be close and converge fast to the global one. When linear kernel is applied, we extend a communication efficient SVRG method to accelerate the training further. Extensive empirical studies validate that our proposed method is highly computational efficient and almost never worsen the generalization. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

FIRE: combining multi-stage filtering with taint analysis for scalable recurring vulnerability detection 24

学校读者我要写书评

暂无评论

FIRE: combining multi-stage filtering with taint analysis fo...

Proceedings of the 33rd USENIX Conference on Security Symposium

作者： Siyue Feng Yueming Wu Wenjie Xue Sikui Pan Deqing Zou Yang Liu Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab and School of Cyber Science and Engineering Huazhong University of Science and Technology China Nanyang Technological University Singapore National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab and School of Cyber Science and Engineering Huazhong University of Science and Technology China and Jinyinhu Laboratory China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab and School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9781939133441

With the continuous development of software open-sourcing, the reuse of open-source software has led to a significant increase in the occurrence of recurring vulnerabilities. These vulnerabilities often arise through the practice of copying and pasting existing vulnerabilities. Many methods have been proposed for detecting recurring vulnerabilities, but they often struggle to ensure both high efficiency and consideration of semantic information about vulnerabilities and patches. In this paper, we introduce FIRE, a scalable method for large-scale recurring vulnerability detection. It utilizes multi-stage filtering and differential taint paths to achieve precise clone vulnerability scanning at an extensive scale. In our evaluation across ten open-source software projects, FIRE demonstrates a precision of 90.0% in detecting 298 recurring vulnerabilities out of 385 ground truth instance. This surpasses the performance of existing advanced recurring vulnerability detection tools, detecting 31.4% more vulnerabilities than VUDDY and 47.0% more than MOVERY. When detecting vulnerabilities in large-scale software, FIRE outperforms MOVERY by saving about twice the time, enabling the scanning of recurring vulnerabilities on an ultra-large scale.

关键词：

Enabling Efficient Large Recommendation Model Training with Near CXL Memory Processing

学校读者我要写书评

暂无评论

Enabling Efficient Large Recommendation Model Training with ...

Annual International Symposium on Computer Architecture, ISCA

作者： Haifeng Liu Long Zheng Yu Huang Jingyi Zhou Chaoqiang Liu Runze Wang Xiaofei Liaot Hai Jinf Jingling Xue National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab Huazhong University of Science and Technology China School of Computer Science and Engineering University of New South Wales Australia Zhejiang Lab Hangzhou China

ISBN: (数字)9798350326581

ISBN: (纸本)9798350326598

Personalized recommendation systems have become one of the most important Internet services nowadays. A critical challenge of training and deploying the recommendation models is their high memory capacity and bandwidth demands, with the embedding layers occupying hundreds of GBs to TBs of storage. The advent of memory disaggregation technology and Compute Express Link (CXL) provides a promising solution for memory capacity scaling. However, relocating memory-intensive embedding layers to CXL memory incurs noticeable performance degradation due to its limited transmission bandwidth, which is significantly lower than the host memory bandwidth. To address this, we introduce ReCXL, a CXL memory disaggregation system that utilizes near-memory processing for scalable, efficient recommendation model training. ReCXL features a unified, hardwareefficient NMP architecture that processes the entire embedding training within CXL memory, minimizing data transfers over the bandwidth-limited CXL and enhancing internal bandwidth. To further improve the performance, ReCXL incorporates softwarehardware co-optimizations, including sophisticated dependencyfree prefetching and fine-grained update scheduling, to maximize hardware utilization. Evaluation results show that ReCXL outperforms the CPU-GPU baseline and the naïve CXL memory by $7.1 \times \sim 10.6 \times(9.4 \times$ on average) and $12.7 \times \sim 31.3 \times(22.6 \times$ on average), respectively.

关键词： Training Degradation Scalability Prefetching Memory management Web and internet services Bandwidth

MeG2: In-Memory Acceleration for Genome Graphs Analysis

学校读者我要写书评

暂无评论

MeG2: In-Memory Acceleration for Genome Graphs Analysis

Design Automation Conference

作者： Yu Huang Long Zheng Haifeng Liu Zhuoran Zhou Dan Chen Pengcheng Yao Qinggang Wang Xiaofei Liao Hai Jin National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory Huazhong University of Science and Technology Wuhan China Zhejiang Lab Hangzhou China

Genome graphs analysis has emerged as an effective means to enable mapping DNA fragments (known as reads) to the reference genome. It replaces the traditional linear reference with a graph-based representation to augment the genetic variations and diversity information, significantly improving the quality of genotyping. The in-depth characterization of genome graphs analysis uncovers that it is bottlenecked by the irregular seed index access and the intensive alignment operation, stressing both the memory system and computing *** on these observations, we propose MeG 2 , a lightweight, commodity DRAM-compliant, processing-in-memory architecture to accelerate genome graphs analysis. MeG 2 is specifically integrated with the capabilities of both near-memory processing and bitwise in-situ computation. Specifically, MeG 2 leverages the low access latency of near-memory processing with the index-centric offload mechanism to alleviate the irregular memory access in the seeding procedure, and harnesses the row-parallel capacity of in-situ computation with the distance-aware technique to exploit the intensive computational parallelism in the alignment process. Results show that MeG 2 outperforms the CPU-, GPU-, and ASIC-based genome graphs analysis solutions by 502× (30.2×), 272× (15.1× ), and 5.5× (8.3×) for short (long) reads, while reducing energy consumption by 1628× (85.6×), 1443× (77.1×), and 7.8× (11.7×), respectively. We also demonstrate that MeG 2 offers significant improvements over existing PIM-based genome sequence analysis accelerators.

关键词：

It Takes Two to Tango: Serverless Workflow Serving via Bilaterally Engaged Resource Adaptation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Jing Wang, Lin Deng, Quanfeng Yu, Chen Zhang, Dong Yan, Bingheng Liu, Fangming National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology China Paderborn University Germany Inspur Data Co. Ltd. China Peng Cheng Laboratory China

Serverless platforms typically adopt an early-binding approach for function sizing, requiring developers to specify an immutable size for each function within a workflow beforehand. Accounting for potential runtime variability, developers must size functions for worst-case scenarios to ensure service-level objectives (SLOs), resulting in significant resource inefficiency. To address this issue, we propose Janus, a novel resource adaptation framework for serverless platforms. Janus employs a late-binding approach, allowing function sizes to be dynamically adapted based on runtime conditions. The main challenge lies in the information barrier between the developer and the provider: developers lack access to runtime information, while providers lack domain knowledge about the workflow. To bridge this gap, Janus allows developers to provide hints containing rules and options for resource adaptation. Providers then follow these hints to dynamically adjust resource allocation at runtime based on real-time function execution information, ensuring compliance with SLOs. We implement Janus and conduct extensive experiments with real-world serverless workflows. Our results demonstrate that Janus enhances resource efficiency by up to 34.7% compared to the state-of-the-art. © 2025, CC BY-NC-ND.

关键词： Resource allocation

FedMHO: Heterogeneous One-Shot Federated Learning Towards Resource-Constrained Edge Devices

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yao, Dezhong Shi, Yuexin Liu, Tongtong Xu, Zhiqiang National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Federated Learning (FL) is increasingly adopted in edge computing scenarios, where a large number of heterogeneous clients operate under constrained or sufficient resources. The iterative training process in conventional FL introduces significant computation and communication overhead, which is unfriendly for resource-constrained edge devices. One-shot FL has emerged as a promising approach to mitigate communication overhead, and model-heterogeneous FL solves the problem of diverse computing resources across clients. However, existing methods face challenges in effectively managing model-heterogeneous one-shot FL, often leading to unsatisfactory global model performance or reliance on auxiliary datasets. To address these challenges, we propose a novel FL framework named FedMHO, which leverages deep classification models on resource-sufficient clients and lightweight generative models on resource-constrained devices. On the server side, FedMHO involves a two-stage process that includes data generation and knowledge fusion. Furthermore, we introduce FedMHO-MD and FedMHO-SD to mitigate the knowledge-forgetting problem during the knowledge fusion stage, and an unsupervised data optimization solution to improve the quality of synthetic samples. Comprehensive experiments demonstrate the effectiveness of our methods, as they outperform state-of-the-art baselines in various experimental setups. Our code is available at https://***/YXShi2000/FedMHO. © 2025, CC BY.

关键词： Federated learning

Does Your Neural Code Completion Model Use My Code? A Membership Inference Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wan, Yao Wan, Guanghua Zhang, Shijie Zhang, Hongyu Zhou, Pan Jin, Hai Sun, Lichao National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Huazhong University of Science and Technology China University of Leigh United States

Recent years have witnessed significant progress in developing deep learning-based models for automated code completion. Examples of such models include CodeGPT and StarCoder. These models are typically trained from a large amount of source code collected from open-source communities such as GitHub. Although using source code in GitHub has been a common practice for training deep-learning-based models for code completion, it may induce some legal and ethical issues such as copyright infringement. In this paper, we investigate the legal and ethical issues of current neural code completion models by answering the following question: Is my code used to train your neural code completion model? To this end, we tailor a membership inference approach (termed CodeMI) that was originally crafted for classification tasks to a more challenging task of code completion. In particular, since the target code completion models perform as opaque black boxes, preventing access to their training data and parameters, we opt to train multiple shadow models to mimic their behavior. The acquired posteriors from these shadow models are subsequently employed to train a membership classifier. Subsequently, the membership classifier can be effectively employed to deduce the membership status of a given code sample based on the output of a target code completion model. We comprehensively evaluate the effectiveness of this adapted approach across a diverse array of neural code completion models, (i.e., LSTM-based, CodeGPT, CodeGen, and StarCoder). Experimental results reveal that the LSTM-based and CodeGPT models suffer the membership leakage issue, which can be easily detected by our proposed membership inference approach with an accuracy of 0.842, and 0.730, respectively. Interestingly, our experiments also show that the data membership of current large language models of code, e.g., CodeGen and StarCoder, is difficult to detect, leaving amper space for further improvement. Finally, we also t

关键词： Deep learning

Fast Parallel Recovery for Transactional Stream Processing on Multicores

学校读者我要写书评

暂无评论

Fast Parallel Recovery for Transactional Stream Processing o...

International Conference on Data Engineering

作者： Jianjun Zhao Haikun Liu Shuhao Zhang Zhuohui Duan Xiaofei Liao Hai Jin Yu Zhang National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Transactional stream processing engines (TSPEs) have gained increasing attention due to their capability of processing real-time stream applications with transactional semantics. However, TSPEs remain susceptible to system failures and power outages. Existing TSPEs mainly focus on performance improvement, but still face a significant challenge to guarantee fault tolerance while offering high-performance services. We revisit commonly-used fault tolerance approaches in stream processing and database systems, and find that these approaches do not work well on TSPEs due to complex data dependencies. In this paper, we propose a novel TSPE called MorphStreamR to achieve fast failure recovery while guaranteeing low performance overhead at runtime. The key idea of MorphStreamR is to record intermediate results of resolved dependencies at runtime, and thus eliminate data dependencies to improve task parallelism during failure recovery. MorphStreamR further mitigates the runtime overhead by selectively tracking data dependencies and incorporating workload-aware log commitment. Experimental results show that MorphStreamR can significantly reduce the recovery time by up to 3.1 x while experiencing much less performance slowdown at runtime, compared with other applicable fault tolerance approaches.

关键词： Fault tolerance Runtime Fault tolerant systems Semantics Parallel processing Real-time systems Power system reliability

On Pipelined GCN with Communication-Efficient Sampling and Inclusion-Aware Caching

学校读者我要写书评

暂无评论

On Pipelined GCN with Communication-Efficient Sampling and I...

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Shulin Wang Qiang Yu Xiong Wang Yuqing Li Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Cyber Science and Engineering Wuhan University Wuhan China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Graph convolutional network (GCN) has achieved enormous success in learning structural information from unstructured data. As graphs become increasingly large, distributed training for GCNs is severely prolonged by frequent cross-worker communications. Existing efforts to improve the training efficiency often come at the expense of GCN performance, while the communication overhead persists. In this paper, we propose PSC-GCN, a holistic pipelined framework for distributed GCN training with communication-efficient sampling and inclusion-aware caching, to address the communication bottleneck while ensuring satisfactory model performance. Specifically, we devise an asynchronous pre-fetching scheme to retrieve stale statistics (features, embedding, gradient) of boundary nodes in advance, such that the embedding aggregation and model update are pipelined with statistics transmission. To alleviate communication volume and staleness effect, we introduce a variance-reduction based sampling policy, which prioritizes inner nodes over boundary ones for reducing the access frequency to remote neighbors, thus mitigating cross-worker statistics exchange. Complementing graph sampling, a feature caching module is co-designed to buffer hot nodes with high inclusion probability, ensuring that frequently sampled nodes will be available in local memory. Extensive evaluations on real-world datasets show the superiority of PSC-GCN over state-of-the-art methods, where we can reduce training time by 72%-80% without sacrificing model accuracy.

关键词： Training Estimation error Accuracy Graph convolutional networks Computational modeling Probability Benchmark testing