检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Dong, Yangjing Fu, Honghao Natarajan, Anand Qin, Minglong Xu, Haochen Yao, Penghui State Key Laboratory for Novel Software Technology New Cornerstone Science Laboratory Nanjing University China Massachusetts Institute of Technology United States State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China Hefei National Laboratory Hefei230088 China

The class MIP∗ of quantum multiprover interactive proof systems with entanglement is much more powerful than its classical counterpart MIP [BFL91, JNV+20b, JNV+20a]: while MIP = NEXP, the quantum class MIP∗ is equal to RE, a class including the halting problem. This is because the provers in MIP∗ can share unbounded quantum entanglement. However, recent works [QY21, QY23] have shown that this advantage is significantly reduced if the provers’ shared state contains noise. This paper attempts to exactly characterize the effect of noise on the computational power of quantum multiprover interactive proof systems. We investigate the quantum two-prover one-round interactive system MIP∗ [poly, o(1)], where the verifier sends polynomially many bits to the provers and the provers send back constantly many bits. We show that noise completely destroys the computational advantage given by shared entanglement in this model. Specifically, we show that if the provers are allowed to share arbitrarily many EPR states, where each EPR state is affected by an arbitrarily small constant amount of noise, the resulting complexity class is equivalent to NEXP = MIP. This improves significantly on the previous best-known bound of NEEEXP (nondeterministic triply exponential time) [QY21]. We also show that this collapse in power is due to noise, rather than the o(1) answer size, by showing that allowing for noiseless EPR states gives the class the full power of RE = MIP∗ [poly, poly]. Along the way, we develop two technical tools of independent interest. First, we give a new, deterministic tester for the positivity of an exponentially large matrix, provided that it has a low-degree Fourier decomposition in terms of Pauli matrices. Secondly, we develop a new invariance principle for smooth matrix functions having bounded third-order Fréchet derivatives or which are Lipschitz continuous. © 2023, CC0.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

Improved Hardness of Approximating k-Clique under ETH

Improved Hardness of Approximating k-Clique under ETH

引用

Annual IEEE Symposium on Foundations of computer science

作者： Bingkai Lin Xuandi Ren Yican Sun Xiuhan Wang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science University of California at Berkeley Berkeley USA School of Computer Science Peking University Beijing China Department of Computer Science Tsinghua University Beijing China

In this paper, we prove that assuming the exponential time hypothesis (ETH), there is no $f(k) \cdot n^{k^{o(1 / \log \log k)}}$-time algorithm that can decide whether an n-vertex graph contains a clique of size k or contains no clique of size $k / 2$, and no FPT algorithm can decide whether an input graph has a clique of size k or no clique of size $k / f(k)$, where $f(k)$ is some function in $k^{1-o(1)}$. Our results significantly improve the previous works [1], [2]. The crux of our proof is a framework to construct gap-producing reductions for the k-CLIQUE problem. More precisely, we show that given an error-correcting code $C: \Sigma_{1}^{k} \rightarrow \Sigma_{2}^{k^{\prime}}$ that is locally testable and smooth locally decodable in the parallel setting, one can construct a reduction which on input a graph G outputs a graph $G^{\prime}$ in $\left(k^{\prime}\right)^{O(1)} \cdot n^{O\left(\log \left|\Sigma_{2}\right| / \log \left|\Sigma_{1}\right|\right)}$ time such•if G has a clique of size k, then $G^{\prime}$ has a clique of size K, where $K=\left(k^{\prime}\right)^{O(1)}$.•if G has no clique of size k, then $G^{\prime}$ has no clique of size $(1-\varepsilon) \cdot K$ for some constant $\varepsilon \in(0,1)$.We then construct such a code with $k^{\prime}=k^{\Theta(\log \log k)}$ and $\left|\Sigma_{2}\right|=\left|\Sigma_{1}\right|^{k^{0.54}}$, establishing the hardness result above. Our code generalizes the derivative code [3] into the case with a super constant order of derivatives.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Video summarization with a graph convolutional attention network

引用

Frontiers of Information technology & Electronic Engineering 2021年第6期22卷 902-913页

作者： Ping LI Chao TANG Xianghua XU School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou 310018China The State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China

Video summarization has established itself as a fundamental technique for generating compact and concise video, which alleviates managing and browsing large-scale video data. Existing methods fail to fully consider the local and global relations among frames of video, leading to a deteriorated summarization performance. To address the above problem, we propose a graph convolutional attention network(GCAN) for video summarization. GCAN consists of two parts, embedding learning and context fusion, where embedding learning includes the temporal branch and graph branch. In particular, GCAN uses dilated temporal convolution to model local cues and temporal self-attention to exploit global cues for video frames. It learns graph embedding via a multi-layer graph convolutional network to reveal the intrinsic structure of frame samples. The context fusion part combines the output streams from the temporal branch and graph branch to create the context-aware representation of frames, on which the importance scores are evaluated for selecting representative frames to generate video summary. Experiments are carried out on two benchmark databases, Sum Me and TVSum, showing that the proposed GCAN approach enjoys superior performance compared to several state-of-the-art alternatives in three evaluation settings.

关键词： Temporal learning Self-attention mechanism Graph convolutional network Context fusion Video summarization

来源：评论

学校读者我要写书评

暂无评论

Tabular insights, visual impacts: transferring expertise from tables to images 24

Tabular insights, visual impacts: transferring expertise fro...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Jun-Peng Jiang Han-Jia Ye Leye Wang Yang Yang Yuan Jiang De-Chuan Zhan School of Artificial Intelligence and National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Key Lab of High Confidence Software Technologies (Peking University) Ministry of Education & School of Computer Science Peking University Beijing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

Transferring knowledge across diverse data modalities is receiving increasing attention in machine learning. This paper tackles the task of leveraging expert-derived, yet expensive, tabular data to enhance image-based predictions when tabular data is unavailable during inference. The primary challenges stem from the inherent complexity of accurately mapping diverse tabular data to visual contexts, coupled with the necessity to devise distinct strategies for numerical and categorical tabular attributes. We propose CHannel tAbulaR alignment with optiMal tranSport (CHARMS), which establishes an alignment between image channels and tabular attributes, enabling selective knowledge transfer that is pertinent to visual features. Specifically, CHARMS measures similarity distributions across modalities to effectively differentiate and transfer relevant tabular features, with a focus on morphological characteristics, enhancing the capabilities of visual classifiers. By maximizing the mutual information between image channels and tabular features, knowledge from both numerical and categorical tabular attributes are extracted. Experimental results demonstrate that CHARMS not only enhances the performance of image classifiers but also improves their interpretability by effectively utilizing tabular knowledge.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Stage Guided Code Generation for Large Language Models

SSRN

引用

SSRN 2024年

作者： Han, Mr Yewei Lyu, Chen Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology School of Information Science and Engineering Shandong Normal University University Road 1 Jinan250014 China

Currently, although Large Language Models have shown significant performance in the field of code generation, their effectiveness in handling complex programming tasks remains limited. This is primarily due to the substantial distance between the problem description and the correct code, making it difficult to ensure accuracy when directly generating code. Human programmers, when faced with a complex programming problem, usually use multiple stages to solve it in order to reduce the difficulty of development. First, they analyze the problem and think about a solution plan, then they design a code architecture based on that plan, and finally they finish writing the detailed code. Based on this, we propose a multi-stage guided code generation strategy that aims to gradually shorten the transformation distance between the problem description and the correct code, thus improving the accuracy of code generation. Specifically, the approach consists of three stages: planning, design and implementation. In the planning phase, the Large Language Model generates a solution plan based on the problem description;in the design phase, the code architecture is further designed based on the solution plan;and in the implementation phase, the previous solution plan and code architecture are utilized to guide the Large Language Model in generating the final code. Additionally, we found that existing competition-level code generation benchmarks may overlap with the training data of the Chat Generative Pre-trained Transformer, posing a risk of data leakage. To validate the above findings and circumvent this risk, we created a competition-level code generation dataset. © 2024, The Authors. All rights reserved.

关键词： Architecture

来源：评论

学校读者我要写书评

暂无评论

Boosting MLPs on Graphs via Distillation in Resource-Constrained Environment

Boosting MLPs on Graphs via Distillation in Resource-Constra...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Zhihui Yang Zhihao Qu Ninghui Jia Shihong Hu Baoliu Ye Deze Zeng Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Science China University of Geosciences Nanjing China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Graph Neural Networks (GNNs) have emerged as a powerful technique across various applications, due to their effective message-passing mechanism. However, their deployment is constrained by limited computational resources, energy concerns, and low-latency processing requirements. While existing works employ logit-based knowledge distillation from GNNs to guide Multilayer Perceptrons (MLPs) training, these methods may lead to reduced accuracy and compromised robustness. These drawbacks arise from two primary factors: the insufficient exploitation of the rich information embedded within the graph structures and the inherent susceptibility of MLPs to noisy data. To tackle these issues, we propose a Mixed Multi-order Knowledge Distillation (MMKD) method, which combines the GNN's logits with hidden layer information through the multi-order distillation to improve the accuracy of the MLP. Moreover, we employ both raw data and perturbed data as input, enhancing the density of knowledge extraction as well as the MLPs' generalization. Extensive experiments across seven benchmark datasets verify the superior performance of our approach in terms of effectiveness and robustness. In comparison with the baseline, our approach achieves an accuracy improvement of up to 8.68% in typical GNN tasks.

关键词： Training Accuracy Multilayer perceptrons Robustness Graph neural networks Data models Noise measurement Data mining Low latency communication Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cervical Segmentation via Alternate Diverse Teaching in Semi-Supervised Learning

Enhancing Cervical Segmentation via Alternate Diverse Teachi...

引用

IEEE International Symposium on Biomedical Imaging

作者： Jiawei Yu College of Computer Science National University of Defense Technology Changsha China State Key Laboratory of Complex & Critical Software Environment Changsha China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

In clinical practice, the cervical structure plays a critical role in predicting preterm birth, thus making accurate segmentation of this structure in ultrasound images of paramount importance. However, the performance of existing deep learning methods is limited by the high cost of labeling ultrasound images. In this context, semi-supervised medical image segmentation techniques have emerged as promising solutions, particularly recent teacher-student frameworks that have demonstrated notable efficacy. Despite their success, these methods are often subject to confirmation bias, which undermines their reliability. To address this issue, we introduce a novel approach, Alternate Diverse Teaching (AD-MT), for the semi-supervised segmentation of cervical ultrasound images. AD-MT enhances model performance by alternately updating two teacher models, offering diverse perspectives during learning. Furthermore, a conftict-combating module is incorporated to ensure that the model learns from the discrepancies between teacher predictions. This methodology effectively harnesses both labeled and unlabeled data for segmentation tasks. Experimental results demonstrate that AD-MT achieves competitive segmentation performance, as evidenced by its strong showing in the ISBI 2025 Fetal Ultrasound Grand Challenge.

关键词： Training Deep learning Image segmentation Ultrasonic imaging Biological system modeling Semisupervised learning Predictive models Reliability Labeling Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Knowledge Concept Recommendation Model for MOOCs with Local Sub-graph Embedding

Knowledge Concept Recommendation Model for MOOCs with Local ...

引用

2022 International Conference on Automation, Robotics and computer Engineering, ICARCE 2022

作者： Ju, Chengcheng Zhu, Yi Wang, Chenyu Jiangsu Normal University Department of Computer Science and Technology Xuzhou China Nanjing University of Aeronautics and Astronautics Ministry of Industry and Information Technology Key Laboratory of Safety-Critical Software Nanjing China

ISBN: (纸本)9781665475488

Massive open online courses (MOOCs) play a crucial role in modern education by providing users with largescale open online learning platforms. Substantial research has been conducted to reduce user learning blindness and improve user experience, particularly in personalized course recommendations based on graph neural networks. However, these efforts have focused primarily on fixed or homogeneous graphs, are vulnerable to data sparsity problems, and are difficult to scale. This study proposes to overcome this limitation using graph convolution on local subgraphs combined with an extended matrix factorization model. First, the proposed method decomposes the heterogeneous graph into multiple meta-path-based subgraphs and combines random wandering sampling methods to capture complex semantic relationships between entities while sampling nodes' influence-rich neighborhoods. Next, the attention mechanism adaptively fuses the contextual information of different subgraphs for a more comprehensive construction of user preferences. Experiments on publicly available MOOCs datasets reveal that the proposed model outperforms other benchmark models and is highly scalable while alleviating the data sparsity problem. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Edge AI Inference as a Service via Dynamic Resources from Repeated Auctions

引用

IEEE Transactions on Mobile Computing 2025年

作者： Ji, Mingtao Zhao, Hehan Jiao, Lei Zhang, Sheng Li, Xin Qian, Zhuzhong Ye, Baoliu Nanjing University State Key Laboratory for Novel Software Technology School of Computer Science Nanjing210023 China University of Oregon Center for Cyber Security and Privacy EugeneOR97403 United States Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing211106 China

To enable edge AI providers to recruit edge devices and use them to deploy AI models and provision inference services, we conduct a comprehensive mathematical and algorithmic study on a novel incentive and optimization mechanism based on repeated auctions. We first model and formulate a time-cumulative social cost optimization problem to capture the challenges of the trade-off between cost and accuracy, the dependency between adjacent auctions, and the need of achieving desired economic properties. Then, to solve this intractable non-linear integer program in an online manner, we design a set of polynomial-time algorithms that work together. Our approach dynamically chooses and switches winning bids under careful control, incorporates online learning to overcome posterior inference accuracy and workload queue dynamics, and leverages randomization to strategically convert fractional decisions of model placement and query dispatch into integers. We also allocate payments to meet the necessary and sufficient conditions for the desired economic properties. Further, we rigorously prove the constant competitive ratio, the sub-linear regret and fit, and the truthfulness and individual rationality for our proposed approach. Finally, through extensive experiments using real devices, AI models, and data traces, we have validated the substantial advantages of our proposed approach compared to the baselines and the state-of-the-art methods. © 2002-2012 IEEE.

关键词： Queueing theory

来源：评论

学校读者我要写书评

暂无评论

A Survey on Large Language Models for software Engineering

arXiv

引用

arXiv 2023年

作者： Zhang, Quanjun Fang, Chunrong Xie, Yang Zhang, Yaxin Yang, Yun Sun, Weisong Yu, Shengcheng Chen, Zhenyu The State Key Laboratory for Novel Software Technology Nanjing University China The School of Computer Science and Engineering Nanyang Technological University Singapore The Department of Computing Technologies Swinburne University of Technology MelbourneVIC3122 Australia

software Engineering (SE) is the systematic design, development, maintenance, and management of software applications underpinning the digital infrastructure of our modern world. Very recently, the SE community has seen a rapidly increasing number of techniques employing Large Language Models (LLMs) to automate a broad range of SE tasks. Nevertheless, existing information of the applications, effects, and possible limitations of LLMs within SE is still not well-studied. In this paper, we provide a systematic survey to summarize the current state-of-the-art research in the LLM-based SE community. We summarize 62 representative LLMs of Code across three model architectures, 15 pre-training objectives across four categories, and 16 downstream tasks across five categories. We then present a detailed summarization of the recent SE studies for which LLMs are commonly utilized, including 947 studies for 112 specific code-related tasks across five crucial phases within the SE workflow. We also discuss several critical aspects during the integration of LLMs into SE, such as empirical evaluation, benchmarking, security and reliability, domain tuning, compressing and distillation. Finally, we highlight several challenges and potential opportunities on applying LLMs for future SE studies, such as exploring domain LLMs and constructing clean evaluation datasets. Overall, our work can help researchers gain a comprehensive understanding about the achievements of the existing LLM-based SE studies and promote the practical application of these techniques. Our artifacts are publicly available and will be continuously updated at the living repository: https://***/iSEngLab/AwesomeLLM4SE. © 2023, CC BY.

关键词： Application programs

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：