检索结果-内蒙古大学图书馆

International Conference on Data Engineering

作者： Guanghui Zhu Zhennan Zhu Wenjie Wang Zhuoer Xu Chunfeng Yuan Yihua Huang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

Many real-world data can be modeled as heterogeneous graphs that contain multiple types of nodes and edges. Meanwhile, due to excellent performance, heterogeneous graph neural networks (GNNs) have received more and more attention. However, the existing work mainly focuses on the design of novel GNN models, while ignoring another important issue that also has a large impact on the model performance, namely the missing attributes of some node types. The handcrafted attribute completion requires huge expert experience and domain knowledge. Also, considering the differences in semantic characteristics between nodes, the attribute completion should be fine-grained, i.e., the attribute completion operation should be node-specific. Moreover, to improve the performance of the downstream graph learning task, attribute completion and the training of the heterogeneous GNN should be jointly optimized rather than viewed as two separate processes. To address the above challenges, we propose a differentiable attribute completion framework called AutoAC for automated completion operation search in heterogeneous GNNs. We first propose an expressive completion operation search space, including topology-dependent and topology-independent completion operations. Then, we propose a continuous relaxation schema and further propose a differentiable completion algorithm where the completion operation search is formulated as a bi-level joint optimization problem. To improve the search efficiency, we leverage two optimization techniques: discrete constraints and auxiliary unsupervised graph node clustering. Extensive experimental results on real-world datasets reveal that AutoAC outperforms the SOTA handcrafted heterogeneous GNNs and the existing attribute completion method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

STSD: Modeling Spatial Temporal Staticity and Dynamicity in Traffic Forecasting

STSD: Modeling Spatial Temporal Staticity and Dynamicity in ...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Guanghui Zhu Haojun Hou Peiliang Wang Chunfeng Yuan Yihua Huang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

As one of the typical tasks of spatial temporal forecasting, traffic prediction has attracted extensive research attention in recent studies. Recent works usually combine time series modeling methods and graph neural networks to capture the temporal dynamic trends and spatial static dependencies together. However, we find that the temporal static characteristic and spatial dynamic correlations do also exist in the traffic flow, which are neglected or partially considered in previous methods. To capture such characteristics, we propose a novel method for traffic prediction, which models the Spatial Temporal Staticity and Dynamicity (STSD) together. Specifically, besides the traditional spatial and temporal encoder, we propose a pre-training module based on self-supervised contrastive learning to learn the location representation and thus capture the temporal static characteristic. Then, we propose a flow-aware dynamic graph learning module to capture the spatial dynamic correlations. Besides, to correct the original graph built from node distance, a feature reconstruction-based static graph learning module is introduced. The original, static, and dynamic graph are combined together in STSD to model the spatial staticity and dynamicity. Extensive experimental results on real-world datasets reveal that STSD can outperform existing traffic forecasting methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Why and How Bug Blocking Relations are Breakable: An Empirical Study on Breakable Blocking Bugs

SSRN

引用

SSRN 2023年

作者： Ren, Hao Li, Yanhui Chen, Lin Zhou, Yuming Nie, Changhai State Key Laboratory for Novel Software Technology Nanjing University 210023 China Department of Computer Science and Technology Nanjing University 210023 China

Context: Blocking bugs prevents other bugs from being fixed, which is difficult to repair and negatively impacts software quality. During software maintenance, developers usually try to break the blocking relationship between blocking and blocked bugs, e.g., propose a temporary ***: However, to our knowledge, no studies have investigated why and how blocking relations between bugs are breakable. In this study, we aim to construct an empirical analysis to explore breakable blocking bugs (BBBs).Method: Specifically, we employ quantitative and qualitative analysis to study these BBBs from two aspects. One is to investigate the characteristics of these bugs, and the other is to explore why and how developers break the blocking relationship between bugs during software maintenance. We build a dataset on five large-scale open-source projects and classify bugs into three types (BBBs, normal blocking bugs, and other bugs) to compare the differences between BBBs and other types of ***: We observe that BBBs are more urgent with the longer fix time and involve more complex source code than other bugs. Moreover, we summarize four reasons blocking relationships between bugs are broken and three approaches developers adopt to break these blocking ***: Through these analyses, it is meaningful for software maintainers to have a deeper understanding of the characteristics and repair practices of BBBs, which will help solve these BBBs effectively in the future. © 2023, The Authors. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

A novel Minimum Attribute Reduction Algorithm Based on Hierarchical Elitist Role Model Combining Competitive and Cooperative Co-evolution

引用

Chinese Journal of Electronics 2023年第4期22卷 677-682页

作者： DING Weiping WANG Jiandong GUAN Zhijin College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China School of Computer Science and Technology Nantong University Nantong China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

Minimum attribute reduction in rough set theory is an NP-hard problem, which is difficult to use traditional evolution methods to solve. In this paper, a novel and efficient minimum Attribute reduction algorithm (named HERCo 2 AR) based on Hierarchical elitist role model combining competitive and cooperative coevolution is proposed. Through such an iterative process of competitive and cooperative co-evolution, the various subpopulations are better optimized by different elitists, and reasonable decomposition of interacting attribute sets can co-adapt to emerge due to the evolutionary pressure of hierarchical elitist role. The hierarchical elitist role model is very effective in the protection and promotion of outstanding individuals, and it can accelerate to direct the global optimal attribute reduction. Experimental results demonstrate that HERCo 2 AR achieves the better feasibility and effectiveness than existing state-of-the-art attribute reduction algorithms, and the quality of the global optimal solution can be significantly improved as well.

关键词： Technological innovation NP-hard problem Education software algorithms Rough sets software Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Research on Indoor Passive Location Based on LoRa Fingerprint 1

引用

6th EAI International Conference on Machine Learning and Intelligent Communications, MLICOM 2021

作者： Wang, Heng Chen, Yuzhen Zhang, Qingheng Zhang, Shifan Ye, Haibo Li, Xuan-Song School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

ISBN: (数字)9783031044090

ISBN: (纸本)9783031044083

Indoor positioning based on signal fingerprint has always been a hot research topic. But most research requires the object or person to be positioned to carry a positioning device, which is not applicable in some special scenarios. This paper selects LoRa (Long Range) as the research target and proposes an indoor passive positioning system based on LoRa fingerprint. We design and implement the signal sent from the LoRa node devices to the LoRa gateway device and get the RSSI of the nodes, also send it to the proxy server for receiving and processing. In the data processing stage, the difference-limiting filtering algorithm is used to eliminate abnormal data, and the GaussianNB (Gaussian-Naive Bayes) algorithm is used to learn and train the model. Through experiments, the accuracy rates of the two-class and multi-class prediction in the range of 3m are 97.1% and 95.5%, respectively, which verifies the feasibility of applying LoRa signal to indoor passive positioning. © 2022, ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Indoor positioning systems

来源：评论

学校读者我要写书评

暂无评论

Non-stationary online learning with memory and non-stochastic control

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 9831-9900页

作者： Peng Zhao Yu-Hu Yan Yu-Xiang Wang Zhi-Hua Zhou National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science University of California Santa Barbara CA

We study the problem of Online Convex Optimization (OCO) with memory, which allows loss functions to depend on past decisions and thus captures temporal effects of learning problems. In this paper, we introduce dynamic policy regret as the performance measure to design algorithms robust to non-stationary environments, which competes algorithms' decisions with a sequence of changing comparators. We propose a novel algorithm for OCO with memory that provably enjoys an optimal dynamic policy regret in terms of time horizon, non-stationarity measure, and memory length. The key technical challenge is how to control the switching cost, the cumulative movements of player's decisions, which is neatly addressed by a novel switching-cost-aware online ensemble approach equipped with a new meta-base decomposition of dynamic policy regret and a careful design of meta-learner and base-learner that explicitly regularizes the switching cost. The results are further applied to tackle non-stationarity in online non-stochastic control (Agarwal et al., 2019), i.e., controlling a linear dynamical system with adversarial disturbance and convex cost functions. We derive a novel gradient-based controller with dynamic policy regret guarantees, which is the first controller provably competitive to a sequence of changing policies for online non-stochastic control.

关键词： online learning online convex optimization with memory online non-stochastic control non-stationary environments dynamic policy regret online ensemble

来源：评论

学校读者我要写书评

暂无评论

AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network

arXiv

引用

arXiv 2023年

作者： Zhu, Guanghui Zhu, Zhennan Wang, Wenjie Xu, Zhuoer Yuan, Chunfeng Huang, Yihua State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science and Technology Nanjing University Nanjing China

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Adversarial Benchmarking of Segment Anything Model on Loss Functions and Multi-Scale Objectives

SSRN

引用

SSRN 2025年

作者： Lv, Huanhuan Jiang, Songru Wan, Tuohang Bai, Yuhao Gou, Chang Chen, Lijun State Key Laboratory for Novel Software Technology Nanjing University Nanjing210036 China School of Computer Science Nanjing University Nanjing210036 China

Segment Anything Model (SAM) and its variants are vulnerable to adversarial examples, which appear benign to humans but can cause the model to make severe mispredictions. This poses critical challenges for their deployment in security-sensitive domains, such as autonomous driving. Existing adversarial benchmarks for SAM and its variants are not comprehensive enough, especially lacking ablations on the loss functions used in adversarial attacks, and analysis on multi-scale objectives. In this paper, we investigate the impact of loss functions employed in adversarial attacks and consideration of various objective scales. First, we benchmark SAM and its variants using 13 loss functions and 3 adversarial attack strategies to evaluate their impact on the mode's robustness. Then, we introduce two novel gradient projection methods, namely tanh and linear, to enhance the efficacy of adversarial attacks. Finally, we examine multi-scale objectives to simulate real-world scenarios, providing insights into SAM's practical applicability. Experiments on the SA-1B dataset demonstrate that the choice of loss functions significantly influences the performance of SAM and its variants. The proposed gradient projection methods further reduce the mIoU and mStep scores. Moreover, the adversarial performance of SAM and its variants exhibits notable differences depending on the multi-scale objectives. Code will be released. © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UltraEdit: Instruction-based Fine-Grained Image Editing at Scale 38

UltraEdit: Instruction-based Fine-Grained Image Editing at S...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhao, Haozhe Ma, Xiaojian Chen, Liang Si, Shuzheng Wu, Rujie An, Kaikai Yu, Peiyu Zhang, Minjia Li, Qing Chang, Baobao National Key Laboratory for Multimedia Information Processing Peking University China State Key Laboratory of General Artificial Intelligence BIGAI China School of Software and Microelectronics Peking University China Department of Computer Science and Technology Tsinghua University China School of Computer Science Peking University China UCLA United States UIUC United States

This paper presents ULTRAEDIT, a large-scale (~4M editing samples), automatically generated dataset for instruction-based image editing. Our key idea is to address the drawbacks in existing image editing datasets like InstructPix2Pix [10] and MagicBrush [71], and provide a systematic approach to producing massive and high-quality image editing samples. ULTRAEDIT offers several distinct advantages: 1) It features a broader range of editing instructions by leveraging the creativity of large language models (LLMs) alongside in-context editing examples from human raters;2) Its data sources are based on real images, including photographs and artworks, which provide greater diversity and reduced bias compared to datasets solely generated by text-to-image models;3) It also supports region-based editing, enhanced by high-quality, automatically produced region annotations. Our experiments show that canonical diffusion-based editing baselines trained on ULTRAEDIT set new records on MagicBrush and Emu-Edit benchmarks. Our analysis further confirms the crucial role of real image anchors and region-based editing data. The dataset, code, and models are available in ***/pkunlp-icler/UltraEdit. © 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

A Crowdsourcing Digital Forensics Platform for IoT Environments Powered by Blockchain

A Crowdsourcing Digital Forensics Platform for IoT Environme...

引用

IEEE International Conference on Communications (ICC)

作者： Yaqing Zhang Xiao Fu Bin Luo Xiaojiang Du State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ USA

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Digital forensics is a security research field that has evolved with the advancement of digital technologies, such as computer and network technology. With the emergence of complex forensic environments, such as those found in the IoT and cloud computing, investigators are required to possess higher technical capabilities and knowledge. Completing digital forensics tasks more effectively has become a challenge. Therefore, this paper proposes a blockchain-based collaborative crowdsourcing platform for digital forensics. Through collaborating on the crowdsourcing platform, professional investigators can enhance the supervision of the digital forensics process, reduce the difficulty of digital forensics tasks, and improve their quality. In addition, we introduce blockchain technology to maintain the credibility of the investigation process. We have developed a smart contract and conducted experiments based on Ethereum. The experimental results show that our solution is feasible.

关键词： Crowdsourcing Technological innovation Digital forensics Smart contracts Collaboration Prediction algorithms Blockchains

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：