检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yikemaiti Sataer Chuanqi Shi Miao Gao Yunlong Fan Bin Li Zhiqiang Gao School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Ministry of Education Nanjing China

Abstract Meaning Representation (AMR) parsing is the task of translating a sentence to an AMR semantic graph which captures the basic meaning of the sentence, and is empowered by pre-trained Transformer models recently. These models encode the syntactic and semantic knowledge implicitly through self-supervised pre-trained tasks. We argue that encoding the syntactic and semantic knowledge explicitly is beneficial to AMR parsing and can improve data efficiency. Specifically, syntactic dependency and semantic role labeling (SRL) have similar sub-structures with AMR. In this work, we propose a novel linguistic knowledge-enhanced AMR parsing model, which augments the pre-trained Transformer with syntactic dependency and semantic role labeling structures of sentences. By applying a heterogeneous graph attention network, we can obtain syntactically and semantically augmented word representation, which can be integrated using an attentive integration layer and gating mechanism. Experimental results show that our model achieves state-of-the-art performance on different benchmarks, especially in out-of-domain and low-resource scenarios.

关键词： Knowledge engineering Semantics Syntactics Linguistics Benchmark testing Signal processing Transformers

来源：评论

学校读者我要写书评

暂无评论

Residual K-Nearest Neighbors Label Distribution Learning

SSRN

引用

SSRN 2023年

作者： Wang, Jing Geng, Xin School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing210096 China

Label Distribution Learning (LDL) is a novel learning paradigm that assigns label distribution to each instance. It aims to learn the label distribution of training instances and predict unknown ones. Algorithm Adaptation (AA)-kNN is one of the most representative LDL baselines that adapts the kNN algorithm to LDL. Its generalization risk has been proven to approach zero if given infinite training data. Despite its theoretical advantage, AA-kNN generally performs poorly because real-world LDL problems only have finite or small training data. In this paper, we improve AA-kNN and propose a novel method called Residual k-Nearest Neighbors Label Distribution Learning (RkNN-LDL). First, RkNN-LDL introduces residual label distribution learning. Second, RkNN-LDL exploits the neighborhood structure of label distribution. We prove that RkNN-LDL has an O( [[EQUATION]] ) generalization bound. Besides, extensive experiments validate that RkNN-LDL beats several state-of-the-art LDL methods and statistically outperforms AA-NN. © 2023, The Authors. All rights reserved.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Adiabatic-Passage-Based Parameter Setting for Quantum Approximate Optimization Algorithm

arXiv

引用

arXiv 2023年

作者： Wu, Mingyou Chen, Hanwu School of Computer Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing211189 China

The Quantum Approximate Optimization Algorithm (QAOA) exhibits significant potential for tackling combinatorial optimization problems. Despite its promise for near-term quantum devices, a major challenge in applying QAOA lies in the cost of circuit runs associated with parameter optimization. Existing methods for parameter setting generally incur at least a superlinear cost concerning the depth p of QAOA. In this study, we propose a novel adiabatic-passage-based parameter setting method that remarkably reduces the optimization cost, specifically when applied to the 3-SAT problem, to a sublinear level. Beginning with an analysis of the random model of the specific problem, this method applies a problem-dependent preprocessing on the problem Hamiltonian analytically, effectively segregating the magnitude of parameters from the scale of the problem. Consequently, a problem-independent initialization is achieved without incurring any optimization cost or pre-computation. Furthermore, the parameter space is adjusted based on the continuity of the optimal adiabatic passage, resulting in a reduction in the disparity of parameters between adjacent layers of QAOA. By leveraging this continuity, the cost to find quasi-optimal parameters is significantly reduced to a sublinear level. © 2023, CC BY.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Inaccurate Label Distribution Learning

arXiv

引用

arXiv 2023年

作者： Kou, Zhiqiang Jia, Yuheng Wang, Jing Geng, Xin The School of Computer Science and Engineering Southeast University Nanjing211189 China The Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing211189 China

Label distribution learning (LDL) trains a model to predict the relevance of a set of labels (called label distribution (LD)) to an instance. The previous LDL methods all assumed the LDs of the training instances are accurate. However, annotating highly accurate LDs for training instances is time-consuming and very expensive, and in reality the collected LD is usually inaccurate and disturbed by annotating errors. For the first time, this paper investigates the problem of inaccurate LDL, i.e., developing an LDL model with noisy LDs. We assume that the noisy LD matrix is a linear combination of an ideal LD matrix and a sparse noise matrix. Consequently, the problem of inaccurate LDL becomes an inverse problem, where the objective is to recover the ideal LD and noise matrices from the noisy LDs. We hypothesize that the ideal LD matrix is low-rank due to the correlation of labels and utilize the local geometric structure of instances captured by a graph to assist in recovering the ideal LD. This is based on the premise that similar instances are likely to share the same LD. The proposed model is finally formulated as a graph-regularized low-rank and sparse decomposition problem and numerically solved by the alternating direction method of multipliers. Furthermore, a specialized objective function is utilized to induce a LD predictive model in LDL, taking into account the recovered label distributions. Extensive experiments conducted on multiple datasets from various real-world tasks effectively demonstrate the efficacy of the proposed approach. Copyright © 2023, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Vision-Language Models are Strong Noisy Label Detectors

arXiv

引用

arXiv 2024年

作者： Wei, Tong Li, Hao-Tian Li, Chun-Shu Shi, Jiang-Xin Li, Yu-Feng Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China

Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a significant obstacle during the fine-tuning process. To address this challenge, this paper presents a Denoising Fine-Tuning framework, called DEFT, for adapting vision-language models. DEFT utilizes the robust alignment of textual and visual features pre-trained on millions of auxiliary image-text pairs to sieve out noisy labels. The proposed framework establishes a noisy label detector by learning positive and negative textual prompts for each class. The positive prompt seeks to reveal distinctive features of the class, while the negative prompt serves as a learnable threshold for separating clean and noisy samples. We employ parameter-efficient fine-tuning for the adaptation of a pre-trained visual encoder to promote its alignment with the learned textual prompts. As a general framework, DEFT can seamlessly fine-tune many pre-trained models to downstream tasks by utilizing carefully selected clean samples. Experimental results on seven synthetic and real-world noisy datasets validate the effectiveness of DEFT in both noisy label detection and image classification tasks. Our source code is available at https://***/HotanLee/DeFT. © 2024, CC BY.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

DLFaaS:Serverless Platform for Data-Intensive Tasks Based on Interval Access Patterns

DLFaaS:Serverless Platform for Data-Intensive Tasks Based on...

引用

IEEE/ACM Int'l Conference on & Int'l Conference on Cyber, Physical and Social Computing (CPSCom) Green Computing and Communications (GreenCom)

作者： Yang Cao Wenbin Song Hanqian Wu Shengchao Yuan School of Computer Science and Engineering Southeast University China School of Cyber Science and Engineering Southeast University China Key Laboratory of Computer Network and Information Integration of Ministry of Education Southeast University China

Serverless architecture is a novel paradigm in cloud computing. The increasing trend in applications is shifting towards serverless platforms to achieve on-demand payment and elastic scalability. However, for data-intensive functions, using serverless architectures can result in performance losses due to frequent data transfers, incurring significant time overhead for data movement. Current serverless systems lack optimization for data migration times in tasks involving data-intensive functions. We conducted an analysis of serverless architecture, function invocation patterns, and latency for data-intensive functions. We found that the lack of awareness of access patterns for these functions leads to inefficient cache eviction, resulting in low cache hit rates. Additionally, bursty calls result in repeated remote storage accesses, contributing to time overhead in dataintensive ***, we proposed a serverless platform based on function invocation patterns, optimized for data-intensive tasks. Specifically, we designed a two-tier caching queue, where data objects accessed multiple times for read and write operations were cached based on historical access patterns. These objects were placed in different cache lists according to various time intervals. We employed an eviction strategy based on function access intervals to enhance overall hit rates. Compared to popular existing solutions, we reduced time latency by 32.1% and improved cache hit rates by 12%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recording Behaviors of Artificial Intelligence in Blockchains

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第6期4卷 1437-1448页

作者： Zhang, Yushu Zhao, Jiahao Jiang, Jiajia Zhu, Youwen Wang, Liangmin Xiang, Yong Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing210023 China Henan Key Laboratory of Network Cryptography Technology Zhengzhou450001 China Southeast University School of Cyber Science and Engineering Nanjing211189 China Deakin University School of Information Technology MelbourneVIC3125 Australia

The key challenges of current blockchain, such as low throughput, high latency, and poor scalability, hinder its future development. The recent advances in artificial intelligence (AI) can well overcome these challenges, thus spurring an increasing number of organizations and individuals to equip blockchain with AI, making blockchain become more intelligent. However, AI behaviors need to be supervised for ex-post forensics in case of dispute and accountability. This motivates us to envision a model to record the AI behaviors in intelligent blockchain. In this article, we propose such a model called AI-Tracer, which leverages proxy re-encryption based on Schnorr signature as well as InterPlanetary File System (IPFS) to be integrated into intelligent blockchain. AI-Tracer generates AI-digest during the AI learning process and encrypts it with proxy re-encryption. IPFS is responsible to store the encrypted AI-digest and returns a hash pointer related to AI-digest for further verification. The authorized user can verify the validity of AI-digest by leveraging advanced features of blockchain technology and only the valid AI-digest can be uploaded to intelligent blockchain, which implements trusted tracking for AI behaviors. AI-Tracer achieves fine-grained access control of AI-digest via proxy re-encryption. A user can retrieve the plaintext of AI-digest from intelligent blockchain with specific authorization. We conduct theoretical analysis to indicate the privacy and security of AI-Tracer. Moreover, we deploy AI-Tracer on the Hyperledger Fabric and demonstrate the efficiency and effectiveness of AI-Tracer through extensive experiments. © 2020 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Gaia: Ground Station-Centric Mobility Management for LEO Satellite networks

Gaia: Ground Station-Centric Mobility Management for LEO Sat...

引用

IEEE International Conference on Communications (ICC)

作者： Xiaxin Zhou Tian Pan Zhaokun Yang Sirui Su Jun Hu Guohao Ruan Junkai Huang Tao Huang Yunjie Liu Beijing University of Posts and Telecommunications Beijing China Purple Mountain Laboratories Nanjing China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

For mega-scale low Earth orbit (LEO) satellite constellations, the relative position changes between satellites and ground terminals pose challenges for end-to-end TCP session maintenance, which serves as the substrate for many Internet services. Mobile IP resolves the session maintenance issue by in-troducing a binding mechanism between the care-of address and home address; however, this also leads to inefficient triangular routing. Our recently proposed LISP-LEO, through partition-satellite mapping, routes traffic to the service satellite above the destination terminal's partition, addressing the triangular routing problem. However, due to the corner case of partition-satellite mapping, LISP-LEO introduces the issue of the last-hop route selection, as well as the associated per-terminal registration states on the satellite, making the solution non-scalable. In this work, we propose Gaia, a ground station-centric mobility management scheme for LEO satellite networks. Gaia maintains a precise mapping of each ground terminal's IP and its geographical location. When receiving traffic from a source terminal, the access satellite can, based on the geographical location of the destination terminal carried by the traffic, directly locate the satellite above the destination terminal and tunnel the traffic to it. In addition, to reduce the satellite's burden, we add a DNS-like querying mechanism by offloading the mapping of terminal IPs and geographical locations to the ground station. The evaluation shows that Gaia outperforms Mobile IP and LISP-LEO in both end-to-end latency and on-board resource consumption.

关键词： Satellite constellations Satellites Web and internet services Low earth orbit satellites Production Routing Maintenance

来源：评论

学校读者我要写书评

暂无评论

D-Router: Decoupled Content Routers with Remote Content Store

D-Router: Decoupled Content Routers with Remote Content Stor...

引用

IEEE International Conference on Communications (ICC)

作者： Shuyi Chen Tian Pan Chunyang Wu Guohao Ruan Jiao Zhang Tao Huang Yunjie Liu Beijing University of Posts and Telecommunications Beijing China Purple Mountain Laboratories Nanjing China Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Named Data networking (NDN) enables efficient content distribution through in-network caching. However, the additional states of network intermediary nodes make NDN forwarding more burdensome, and the unpredictability of cache hits during forwarding leads to uncertain content retrieval latency. To overcome performance bottlenecks at the router's data plane and enhance network determinism, we propose the decoupled content router with remote content store (D-Router). This novel architecture decouples the local content store (CS) from routers and introduces the remote CS device for pooling important content. When Interest packets arrive at a router whose CS is overloaded, we ensure determinism by forwarding them to the remote CS for processing if the requested content is cached there, preventing blocking before the local CS of routers and potential random cache hits along the forwarding path. The dual-path bypass forwarding is supported through the design of routers and a dual-path routing protocol. D-Router is compatible with traditional NDN. Experiments show notable enhancements in data plane performance, including a 30% reduction in round-trip time (RTT), a 25% increase in throughput, improved determinism, and reduced network jitter. Additionally, the decoupling of CS makes it easier for network administrators to deploy network upgrades.

关键词： Performance evaluation Jitter Throughput Routing protocols

来源：评论

学校读者我要写书评

暂无评论

A VLAN-based network Testbed for Lightweight Satellite Constellation Emulation

A VLAN-based Network Testbed for Lightweight Satellite Const...

引用

IEEE International Conference on Communications (ICC)

作者： Yan Zheng Tian Pan Yan Zhang Jiang Liu Tao Huang Yunjie Liu Purple Mountain Laboratories Nanjing China Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Considering the high costs of satellite manufacturing and launch, as well as the complexity of in-orbit debugging, pre-launch emulation on the ground will significantly reduce the development costs of low Earth orbit (LEO) satellite networks. LEO satellite network emulation faces challenges in emulating mega-scale constellations in a lightweight and scalable manner, as well as efficiently handling the frequent link on/off switching for both inter-satellite networks and terrestrial access networks. Existing simulation/emulation tools, such as NS-3, Mininet, QualNet, fall short in addressing these issues effectively. In this work, we propose a lightweight satellite emulation testbed based on Docker containers and the VLAN protocol. In the data plane, our testbed uses Docker containers to emulate satellites/terminals, and uses VETH-pairs and bridges to emulate inter-satellite networks and terrestrial access networks. Furthermore, these virtual network elements can horizontally scale across multiple servers for mega-scale constellation emulation. In the control plane, the real-time constellation topology changes are efficiently emulated through the configuration of VLAN segmentation according to satellite movement patterns. Evaluation shows the testbed's low resource occupancy and high efficiency, with 100 nodes consuming only 1000MB memory and 100 links switching in less than 2s.

关键词： Satellite constellations Satellites Costs Emulation Low earth orbit satellites Switches Containers

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：