检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Yanlin Huang, Yanxian Guo, Daya Zhang, Hongyu Zheng, Zibin School of Software Engineering Sun Yat-sen University China School of Computer Science and Technology Sun Yat-sen University China School of Big Data and Software Engineering Chongqing University China

Code summarization aims to generate natural language descriptions of source code, facilitating programmers to understand and maintain it rapidly. While previous code summarization efforts have predominantly focused on method-level, this paper studies file-level code summarization, which can assist programmers in understanding and maintaining large source code projects. Unlike method-level code summarization, file-level code summarization typically involves long source code within a single file, which makes it challenging for Transformer-based models to understand the code semantics for the maximum input length of these models is difficult to set to a large number that can handle long code input well, due to the quadratic scaling of computational complexity with the input sequence length. To address this challenge, we propose SparseCoder, an identifier-aware sparse transformer for effectively handling long code sequences. Specifically, the SparseCoder employs a sliding window mechanism for self-attention to model short-term dependencies and leverages the structure message of code to capture long-term dependencies among source code identifiers by introducing two types of sparse attention patterns named global and identifier attention. To evaluate the performance of SparseCoder, we construct a new dataset FILE-CS for file-level code summarization in Python. Experimental results show that our SparseCoder model achieves state-of-the-art performance compared with other pretrained models, including full self-attention and sparse models. Additionally, our model has low memory overhead and achieves comparable performance with models using full self-attention mechanism. Furthermore, we verify the generality of SparseCoder on other code understanding tasks, i.e., code clone detection and code search, and results show that our model outperforms baseline models in both tasks, demonstrating that our model can generate better code representations for various downstream tasks. Our

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-Normal Prototypes Learning for Weakly Supervised Anomaly Detection

arXiv

引用

arXiv 2024年

作者： Dong, Zhijin Liu, Hongzhi Ren, Boyuan Xiong, Weimin Wu, Zhonghai School of Software and Microelectronics Peking University Beijing China School of Computer Science Peking University Beijing China National Engineering Center of Software Engineering Peking University Beijing China

Anomaly detection is a crucial task in various domains. Most of the existing methods assume the normal sample data clusters around a single central prototype while the real data may consist of multiple categories or subgroups. In addition, existing methods always assume all unlabeled samples are normal while some of them are inevitably being anomalies. To address these issues, we propose a novel anomaly detection framework that can efficiently work with limited labeled anomalies. Specifically, we assume the normal sample data may consist of multiple subgroups, and propose to learn multi-normal prototypes to represent them with deep embedding clustering and contrastive learning. Additionally, we propose a method to estimate the likelihood of each unlabeled sample being normal during model training, which can help to learn more efficient data encoder and normal prototypes for anomaly detection. Extensive experiments on various datasets demonstrate the superior performance of our method compared to state-of-the-art methods. Our codes are available at: https://***/Dongzhijin/MNPWAD Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Generalized Stochastic Petri Net Based Simulation of IoT Supported Dynamic Navigation in Teaching Building Evacuation

Generalized Stochastic Petri Net Based Simulation of IoT Sup...

引用

2022 International Conference on Cyber-Physical Social Intelligence, ICCSI 2022

作者： Strobing, Jordan Granit, Meghan Wang, Jiacun Zhao, Lin Monmouth University Dept. of Computer Science and Software Engineering NJ United States School of Safety Science and Engineering Xi'an Univ. of Sci. and Tech Xi'an China

ISBN: (数字)9781665498357

ISBN: (纸本)9781665498357

Emergency management and evacuation efficiency is important to ensure the safety of faculty and students in college. Teaching buildings are typically of multiple stories. When classes are in session, a teaching building may have a large number of students inside. In case of an event like a fire, people have to be evacuated as soon as possible. Due to panic, people may not use good judgement to choose optimal evacuation path, which can further cause congestion in a path to an exit. This study attempts to leverage the recent advances in information technology to dynamically guide evacuees. We use generalized stochastic Petri nets (GSPN) to model the evacuation process in a teaching building. The layout of the building, sizes of classrooms and hallways, number of people in each room, and people's decision pattern in choosing a direction to move are all parameters of the model. With simulation we can estimate the evacuation time-span. Moreover, by observing the state of GSPN model, we can analyze the congestion status of each simulated pathway, and based on that we can dynamically notify people to select the right path that lead them to an exit with the least amount of time. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Understanding Heterophily for Graph Neural Networks 41

Understanding Heterophily for Graph Neural Networks

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Junfu Guo, Yuanfang Yang, Liang Wang, Yunhong State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China Shen Yuan Honors College Beihang University Beijing China School of Artificial Intelligence Hebei University of Technology Tianjin China

Graphs with heterophily have been regarded as challenging scenarios for Graph Neural Networks (GNNs), where nodes are connected with dissimilar neighbors through various patterns. In this paper, we present theoretical understandings of heterophily for GNNs by incorporating the graph convolution (GC) operations into fully connected networks via the proposed Heterophilous Stochastic Block Models (HSBM), a general random graph model that can accommodate diverse heterophily patterns. Our theoretical investigation comprehensively analyze the impact of heterophily from three critical aspects. Firstly, for the impact of different heterophily patterns, we show that the separability gains are determined by two factors, i.e., the Euclidean distance of the neighborhood distributions and pE [deg], where E [deg] is the averaged node degree. Secondly, we show that the neighborhood inconsistency has a detrimental impact on separability, which is similar to degrading E [deg] by a specific factor. Finally, for the impact of stacking multiple layers, we show that the separability gains are determined by the normalized distance of the lpowered neighborhood distributions, indicating that nodes still possess separability in various regimes, even when over-smoothing occurs. Extensive experiments on both synthetic and real-world data verify the effectiveness of our theory. Copyright 2024 by the author(s)

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Method of Image Restoration Technology Based on WGAN

引用

computer Systems science & engineering 2022年第5期41卷 689-698页

作者： Wei Fang Enming Gu Weinan Yi Weiqing Wang Victor S.Sheng School of Computer&Software Engineering Research Center of Digital ForensicsMininstry of EducationNanjing University of Information Science&TechnologyNanjing210044China Provincial Key Laboratory for Computer Information Processing Technology Soochow UniversitySuzhou215325China Texas Tech University USA

With the development of image restoration technology based on deep learning,more complex problems are being solved,especially in image semantic inpainting based on ***,image semantic inpainting techniques are becoming more ***,due to the limitations of memory,the instability of training,and the lack of sample diversity,the results of image restoration are still encountering difficult problems,such as repairing the content of glitches which cannot be well integrated with the original ***,we propose an image inpainting network based on Wasserstein generative adversarial network(WGAN)*** the corresponding technology having been adjusted and improved,we attempted to use the Adam algorithm to replace the traditional stochastic gradient descent,and another algorithm to optimize the training used in recent *** evaluated our algorithm on the ImageNet *** obtained high-quality restoration results,indicating that our algorithm improves the clarity and consistency of the image.

关键词： Image restoration WGAN DCGAN context semantic

来源：评论

学校读者我要写书评

暂无评论

Property Enhanced Instruction Tuning for Multi-task Molecule Generation with Large Language Models

arXiv

引用

arXiv 2024年

作者： Lin, Xuan Chen, Long Wang, Yile Zeng, Xiangxiang Yu, Philip S. School of Computer Science Xiangtan University China College of Computer Science and Software Engineering Shenzhen University China College of Information Science and Engineering Hunan University China Department of Computer Science University of Illinois United States

Large language models (LLMs) are widely applied in various natural language processing tasks such as question answering and machine translation. However, due to the lack of labeled data and the difficulty of manual annotation for biochemical properties, the performance for molecule generation tasks is still limited, especially for tasks involving multi-properties constraints. In this work, we present a two-step framework PEIT (Property Enhanced Instruction Tuning) to improve LLMs for molecular-related tasks. In the first step, we use textual descriptions, SMILES, and biochemical properties as multimodal inputs to pre-train a model called PEIT-GEN, by aligning multimodal representations to synthesize instruction data. In the second step, we fine-tune existing open-source LLMs with the synthesized data, the resulting PEIT-LLM can handle molecule captioning, text-based molecule generation, molecular property prediction, and our newly proposed multi-constraint molecule generation tasks. Experimental results show that our pre-trained PEIT-GEN outperforms MolT5, BioT5, MolCA and Text+Chem-T5 in molecule captioning, demonstrating modalities align well between textual descriptions, structures, and biochemical properties. Furthermore, PEIT-LLM shows promising improvements in multi-task molecule generation, demonstrating the effectiveness of the PEIT framework for various molecular tasks. We release the code, constructed instruction data, and model checkpoints in https://***/chenlong164/PEIT. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Unikdd: A Unified Generative Model for Knowledge-Driven Dialogue

SSRN

引用

SSRN 2024年

作者： Wang, Qian Chen, Yan Wang, Yang Wang, Xu School of Computer Science and Software Engineering Southwest Petroleum University Chengdu610500 China College of Computer Science Sichuan University Chengdu610065 China

knowledge-driven dialogue (KDD) is to introduce an external knowledge base,generating an informative and fluent response. However, previous works employ different models to conduct the sub-tasks of KDD, ignoring the connection between sub-tasks and resulting in a difficulty of training and inference. Tosolve those issues above, we propose the UniKDD, a unified generative model for KDD, which models all sub-tasks into a generation task, enhancing the connection between tasks and facilitating the training and inference. Specifically, UniKDD simplifies the complex KDD tasks into three main sub-tasks, i.e., entity prediction, attribute prediction, and dialogue generation. These tasks are transformed into a text generation task and trained by an end-to-end way. In the inference phase, UniKDD first predicts a set of entities used for current turn dialog according to the dialogue history. Then, for each predicted entity, UniKDD predicts the corresponding attributes by the dialogue history. Finally, UniKDD generates a high-quality and informative response using the dialogue history and predicted knowledge triplets. The experimental results show that our proposed UniKDD can perform KDD task well and outperform the baseline on the evaluation of knowledge selection and response generation. The code is available athttps://***/qianandfei/***. © 2024, The Authors. All rights reserved.

关键词： Petroleum reservoir evaluation

来源：评论

学校读者我要写书评

暂无评论

Revisiting Multi-Agent Asynchronous Online Optimization with Delays: the Strongly Convex Case

arXiv

引用

arXiv 2025年

作者： Bao, Lingchan Wei, Tong Wan, Yuanyu School of Computer Science and Engineering Southeast University Nanjing211189 China School of Software Technology Zhejiang University Ningbo315100 China

We revisit multi-agent asynchronous online optimization with delays, where only one of the agents becomes active for making the decision at each round, and the corresponding feedback is received by all the agents after unknown delays. Although previous studies have established an O(√dT) regret bound for this problem, they assume that the maximum delay d is knowable or the arrival order of feedback satisfies a special property, which may not hold in practice. In this paper, we surprisingly find that when the loss functions are strongly convex, these assumptions can be eliminated, and the existing regret bound can be significantly improved to O(dlog T) meanwhile. Specifically, to exploit the strong convexity of functions, we first propose a delayed variant of the classical follow-the-leader algorithm, namely FTDL, which is very simple but requires the full information of functions as feedback. Moreover, to handle the more general case with only the gradient feedback, we develop an approximate variant of FTDL by combining it with surrogate loss functions. Experimental results show that the approximate FTDL outperforms the existing algorithm in the strongly convex case. Copyright © 2025, The Authors. All rights reserved.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

A Self-Distillation Assisted ResNet-KL Image Classification Network

A Self-Distillation Assisted ResNet-KL Image Classification ...

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Yuanyuan Wang Haiyang Tian Shaofeng Yan Junxun Zhu Zhaoyu Song Yu Shen School of Computer Science and Software Engineering Huaiyin Institute of Technolog Huai’an China

Traditional ResNet models suffer from large model size and high computational complexity. In this study, we propose a self-distillation assisted ResNet-KL image classification method to address the low accuracy and efficiency issues in image classification ***,we introduce depthwise separable convolutions to the ResNet network and enhance the model’s classification performance by improving the design of activation functions, using TReLU instead of traditional ReLU. Secondly,we enhance the model’s perception of features at different scales by incorporating multi-scale convolutions for the fusion of residual layers and attention mechanism layers. To reduce the model’s parameter count, we combine feature distillation with logic distillation and optimize the model layer by layer through selfdistillation, while applying pruning techniques multiple times to reduce its size. Finally, To assess the efficacy of our methodology, we conduct experimental evaluations on public datasets CIFAR-10, CIFAR-100, and STL-10. The results show that the improved ResNet-KL network achieves an accuracy improvement of 1.65%, 2.72%, and 0.36% compared to traditional ResNet models on these datasets, respectively. Our method obtains better classification performance with the same computational resources, making it promising for applications in tasks such as object classification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Metric Ranking with Label Correlations Approach for Library Migration Recommendations

A Multi-Metric Ranking with Label Correlations Approach for ...

引用

IEEE International Conference on software Analysis, Evolution and Reengineering (SANER)

作者： Jiancheng Zhang Qin Luo Peng Wu School of Computer Science and Software Engineering SouthWest Petroleum University Chengdu China School of Information and Engineering Sichuan Tourism University Chengdu China

ISBN: (数字)9798350330663

ISBN: (纸本)9798350330670

While third-party libraries provide benefit to software systems, they also bring unique challenges. It often happens that developers need to replace some already-used libraries with other functionality-equivalent libraries. However, it is not easy to find a relevant candidate from overwhelming libraries. Despite several approaches have been proposed to mine library migrations from historical data, the study of library recommendation from the perspective of both open-source projects and third-party libraries is lacking. Therefore, conducting such research may assist developer better select suitable third-party libraries. In this paper, we propose a multi-metric ranking with label correlations (MMRLC) algorithm, which can recommend libraries holistically from the both perspectives. Not only does it mine library migrations from existing software data, MMRLC further leverages label correlations of libraries in Maven Central Repository to make recommendations. To demonstrate the usefulness, three popular algorithms were conducted on a benchmark dataset for comparison. The results show that our approach can recommend libraries with precision @ 1 of 0.8454 and recall @20 of 0.9301. Moreover, to demonstrate the generality, we select 366 libraries and resort to TagWiki to generate the related library labels, and the results show that our approach still has comparable performance.

关键词： Electronic publishing Correlation software algorithms Buildings Benchmark testing software systems Libraries

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：