检索结果-内蒙古大学图书馆

SmartZone: Runtime Support for Secure and Efficient On-Device Inference on ARM TrustZone

IEEE Transactions on Computers 2025年第6期74卷 2144-2158页

作者： Jian, Zhaolong Liu, Xu Dong, Qiankun Cheng, Longkai Xie, Xueshuo Li, Tao Nankai University College of Computer Science Tianjin300350 China Tianjin Key Laboratory of Network and Data Science Technology Tianjin300350 China Haihe Lab of ITAI Tianjin300450 China

On-device inference is a burgeoning paradigm that performs model inference locally on end devices, allowing private data to remain local. ARM TrustZone as a widely supported trusted execution environment has been applied to provide confidentiality protection for on-device inference. However, with the rise of large-scale models like large language models (LLMs), TrustZone-based on-device inference faces challenges in migration difficulties and inefficient execution. The rudimentary TEE OS on TrustZone lacks both the inference runtime needed for building models and the parallel support necessary to accelerate inference. Moreover, the limited secure memory resources on end devices further constrain the model size and degrade performance. In this paper, we propose SmartZone to provide runtime support for secure and efficient on-device inference on TrustZone. SmartZone consists three main components: (1) a trusted inference-oriented operator set, providing the underlying mechanisms adapted to the TrustZone’s execution mode for trusted inference of DNN models and LLMs. (2) the proactive multi-threading parallel support, which increases the number of CPU cores in the secure state via cross-world thread collaboration to achieve parallelism, and (3) the on-demand secure memory management method, which statically allocates the appropriate secure memory size based on pre-execution resource analysis. We implement a prototype of SmartZone on the Raspberry Pi 3B+ board and evaluate it on four well-known DNN models and llama2 LLM. Extensive experimental results show that SmartZone provides end-to-end protection for on-device inference while maintaining excellent performance. Compared to the origin trusted inference, SmartZone accelerates the inference speed by up to 4.26× and reduces energy consumption by 65.81%. © 1968-2012 IEEE.

关键词： Memory management

来源：评论

学校读者我要写书评

暂无评论

Nested Event Extraction upon Pivot Element Recognition 30

Nested Event Extraction upon Pivot Element Recognition

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Ren, Weicheng Li, Zixuan Jin, Xiaolong Bai, Long Su, Miao Liu, Yantao Guan, Saiping Guo, Jiafeng Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences China Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9782493814104

Nested Event Extraction (NEE) aims to extract complex event structures where an event contains other events as its arguments recursively. Nested events involve a kind of Pivot Elements (PEs) that simultaneously act as arguments of outer-nest events and as triggers of inner-nest events, and thus connect them into nested structures. This special characteristic of PEs brings challenges to existing NEE methods, as they cannot well cope with the dual identities of PEs. Therefore, this paper proposes a new model, called PerNee, which extracts nested events mainly based on recognizing PEs. Specifically, PerNee first recognizes the triggers of both inner-nest and outer-nest events and further recognizes the PEs via classifying the relation type between trigger pairs. The model uses prompt learning to incorporate information from both event types and argument roles for better trigger and argument representations to improve NEE performance. Since existing NEE datasets (e.g., Genia11) are limited to specific domains and contain a narrow range of event types with nested structures, we systematically categorize nested events in the generic domain and construct a new NEE dataset, called ACE2005-Nest. Experimental results demonstrate that PerNee consistently achieves state-of-the-art performance on ACE2005-Nest, Genia11, and Genia13. The ACE2005-Nest dataset and the code of the PerNee model are available at https://***/waysonren/PerNee. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework

Controlling Risk of Retrieval-augmented Generation: A Counte...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Chen, Lu Zhang, Ruqing Guo, Jiafeng Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798891761681

Retrieval-augmented generation (RAG) has emerged as a popular solution to mitigate the hallucination issues of large language models. However, existing studies on RAG seldom address the issue of predictive uncertainty, i.e., how likely it is that a RAG model's prediction is incorrect, resulting in uncontrollable risks in real-world applications. In this work, we emphasize the importance of risk control, ensuring that RAG models proactively refuse to answer questions with low confidence. Our research identifies two critical latent factors affecting RAG's confidence in its predictions: the quality of the retrieved results and the manner in which these results are utilized. To guide RAG models in assessing their own confidence based on these two latent factors, we develop a counterfactual prompting framework that induces the models to alter these factors and analyzes the effect on their answers. We also introduce a benchmarking procedure to collect answers with the option to abstain, facilitating a series of experiments. For evaluation, we introduce several risk-related metrics and the experimental results demonstrate the effectiveness of our approach. Our code and benchmark dataset are available at https://***/ictbigdatalab/RC-RAG. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Beyond Precision: A Study on Recall of Initial Retrieval with Neural Representations 1

引用

28th China Conference on Information Retrieval, CCIR 2022

作者： Xiao, Yan Fan, Yixing Zhang, Ruqing Guo, Jiafeng CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

ISBN: (数字)9783031247552

ISBN: (纸本)9783031247545

Vocabulary mismatch is a central problem in information retrieval (IR), i.e., the relevant documents may not contain the same (symbolic) terms of the query. Recently, neural representations have shown great success in capturing semantic relatedness, leading to new possibilities to alleviate the vocabulary mismatch problem in IR. However, most existing efforts in this direction have been devoted to the re-ranking stage. That is to leverage neural representations to help re-rank a set of candidate documents, which are typically obtained from an initial retrieval stage based on some symbolic index and search scheme (e.g., BM25 over the inverted index). This naturally raises a question: if the relevant documents have not been found in the initial retrieval stage due to vocabulary mismatch, there would be no chance to re-rank them to the top positions later. Therefore, in this paper, we study the problem how to employ neural representations to improve the recall of relevant documents in the initial retrieval stage. Specifically, to meet the efficiency requirement of the initial stage, we introduce a neural index for the neural representations of documents, and propose two hybrid search schemes based on both neural and symbolic indices, namely the parallel search scheme and the sequential search scheme. Our experiments show that both hybrid index and search schemes can improve the recall of the initial retrieval stage with small overhead. © 2023, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Generative Retrieval Meets Multi-Graded Relevance 38

Generative Retrieval Meets Multi-Graded Relevance

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Tang, Yubao Zhang, Ruqing Guo, Jiafeng de Rijke, Maarten Chen, Wei Cheng, Xueqi CAS Key Lab of Network Data Science and Technology ICT CAS China University of Chinese Academy of Sciences China University of Amsterdam Netherlands

Generative retrieval represents a novel approach to information retrieval. It uses an encoder-decoder architecture to directly produce relevant document identifiers (docids) for queries. While this method offers benefits, current approaches are limited to scenarios with binary relevance data, overlooking the potential for documents to have multi-graded relevance. Extending generative retrieval to accommodate multi-graded relevance poses challenges, including the need to reconcile likelihood probabilities for docid pairs and the possibility of multiple relevant documents sharing the same identifier. To address these challenges, we introduce a framework called GRaded Generative Retrieval (GR2). GR2 focuses on two key components: ensuring relevant and distinct identifiers, and implementing multi-graded constrained contrastive training. First, we create identifiers that are both semantically relevant and sufficiently distinct to represent individual documents effectively. This is achieved by jointly optimizing the relevance and distinctness of docids through a combination of docid generation and autoencoder models. Second, we incorporate information about the relationship between relevance grades to guide the training process. We use a constrained contrastive training strategy to bring the representations of queries and the identifiers of their relevant documents closer together, based on their respective relevance grades. Extensive experiments on datasets with both multi-graded and binary relevance demonstrate the effectiveness of GR. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Flexible TiO_(2)-WO_(3−x) hybrid memristorwith enhanced linearity and synaptic plasticity for precise weight tuning in neuromorphic computing

引用

npj Flexible Electronics 2024年第1期8卷 180-191页

作者： Jianyong Pan Hao Kan Zhaorui Liu Song Gao Enxiu Wu Yang Li Chunwei Zhang Shandong Provincial Key Laboratory of Network Based Intelligent Computing School of Information Science and EngineeringUniversity of JinanJinanChina State Key Lab of Transducer Technology Shanghai Institute of Microsystem and Information TechnologyChinese Academy of SciencesShanghaiChina School of Integrated Circuits Shandong UniversityJinanChina

Tungsten oxide(WO_(3))-based memristors show promising applications in neuromorphic ***,single-layer WO_(3) memristors suffer from issues such as weak memory performance and nonlinear conductance *** this work,a functional layer based on the hybrids of WO_(3−x) and TiO_(2) is proposed for constructing flexible memristors featuring outstanding synaptic *** diverse electrical stimulations to the memristor enables a range of synaptic functions,elucidating its conduction mechanism through the conductive filament *** incorporation of TiO_(2) not only enhances the memristor’s memory characteristics but makes its conductance more linear,symmetrical and uniform during the long-term ***,in view of the enhanced device performance by TiO_(2) doping,the potential of this device for simple behavioral simulation and processing of complex computing problems is ***“learning-forgetting-relearning”characteristics and device integrability are visually *** the device to a convolutional neural network,the recognition accuracy of MNIST handwritten digits reaches 98.7%.

关键词： computing tuning precise

来源：评论

学校读者我要写书评

暂无评论

DP-GenFL: a local differentially private federated learning system through generative data

引用

science China(Information sciences) 2023年第8期66卷 275-276页

作者： Jun LI Kang WEI Chuan MA Feng SHU School of Electronic and Optical Engineering Nanjing University of Science and Technology Zhejiang Lab Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education School of Information and Communication Engineering Hainan University

With the rapid development of the Internet of Things(Io T),the amount of data from intelligent devices is propagating at unprecedented scales. Meanwhile, machine learning(ML),which relies heavily on such data, is revolutionizing many aspects of our lives [1]. However, conventional centralized ML offers little scalability for efficiently processing this huge amount of data.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

BrainPST: Pre-training Stacked Transformers for Dynamic Brain Functional network Analysis

BrainPST: Pre-training Stacked Transformers for Dynamic Brai...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Hu, Jinlong Huang, Yangmin Zhuo, Yi Dong, Shoubin South China University of Technology Guangdong Key Lab of Communication and Computer Network School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9798350337488

Deep learning methods have been applied for dynamic brain functional network analysis recently. However, they are usually restricted by the complex spatio-temporal dynamics and the limited labeled data. In this paper, we proposed a stacked Transformer neural network, namely BrainPST, to capture spatio-temporal patterns for dynamic brain functional network classification. BrainPST model integrated spatial and temporal information by stacking two Transformers: one for learning snapshot networks and the other for learning sequence of functional connections. Unlike recent models, BrainPST was designed to pre-train the stacked Transformer network by leveraging unlabeled existing brain imaging data. A pre-training framework with designed pre-training strategies was proposed to learn general spatio-temporal representations from the unlabeled brain networks, and to fine-tune the pre-trained model in downstream tasks. BrainPST is a conceptually simple and effective model. The results of experiments showed the BrainPST model without pre-training achieved comparative performance with the recent models, and the pre-trained BrainPST obtained new state-of-the-art performance. The pre-trained BrainPST improved 3.92% of AUC compared with the model without pre-training. © 2023 IEEE.

关键词： Classification Dynamic brain functional networks Pre-training Transformer

来源：评论

学校读者我要写书评

暂无评论

Prediction of Potential Repurposed Drugs against SARS-CoV-2 based on Text Mining and Molecular Docking Analysis 6

Prediction of Potential Repurposed Drugs against SARS-CoV-2 ...

引用

6th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2023

作者： Zhou, Jie Xu, Yi-Qing Guangdong Key Lab of Communication and Computer Network School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798400707674

Many research papers focusing the relationships between drugs and coronavirus-related protein interactions are indexed in the PubMed database. These studies provide a reference for predicting potential repurposed drugs against SARS-CoV-2. Drug repurposing, the most efficient strategy to quickly deploy new effective therapeutic drugs against SARS-CoV-2, can shorten the time and reduce the cost compared to de novo drug discovery. The purpose of this study was to predict potential repurposed drugs and drug pairs against SARS-CoV-2 using text mining and molecular docking analysis. We first constructed a coronavirus-related protein names list and a drug names list using the relevant protein and drug databases. We also constructed a qualifier list. A crawler program was implemented to retrieve the desired parts from the relevant papers in the PubMed database using records from the three query lists. Based on these extracted parts, we constructed a document set, a document drug names set, and a document protein names set. Then, we used the method proposed in our previous work to calculate the document vector of each document in the document set and the TF, IDF, and TF-IDF values. We calculated the vectors of each drug and protein in the document drug names set and document protein names set based on the document vectors. The cosine similarity between the protein vector and drug vector was calculated and the score of the pair of protein and drug was defined by the cosine similarity. Next, we selected the protein-drug pairs that scored above a given threshold as the predicted interactions for coronavirus-related protein-drug pairs and then extracted all the drugs from these predicted interactions and combined them to form distinct drug pairs. Finally, the drugs with PubChem 3D structure were simulated by a molecular docking tool with the four recently identified important SARS-CoV-2 proteins, and the drug pairs were simulated by the molecular docking tool with the SARS-CoV-2

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Transformer and Snowball Graph Convolution Learning for Brain Functional network Analysis

Transformer and Snowball Graph Convolution Learning for Brai...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Hu, Jinlong Huang, Yangmin Dong, Shoubin South China University of Technology Guangdong Key Lab of Communication and Computer Network School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9798350337488

Advanced deep learning methods, especially graph neural networks (GNNs), are increasingly expected to learn from brain functional network data and predict brain disorders. In this paper, we proposed a novel Transformer and snowball encoding networks (TSEN) for brain functional network classification, which introduced Transformer architecture with graph snowball connection into GNNs for learning whole-graph representation. TSEN combined graph snowball connection with graph Transformer by snowball encoding layers, which enhanced the power to capture multi-scale information and global patterns of brain functional networks. TSEN also introduced snowball graph convolution as position embedding in Transformer structure, which was a simple yet effective method for capturing local patterns naturally. We evaluated the proposed model by two large-scale brain functional network datasets from autism spectrum disorder and major depressive disorder respectively, and the results demonstrated that TSEN outperformed the state-of-the-art GNN models and the graph-transformer based GNN models. © 2023 IEEE.

关键词： Brain disorders Graph neural networks Snowball graph convolutional networks Transformer

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：