检索结果-内蒙古大学图书馆

International Conference on software Engineering (ICSE)

作者： Zhensu Sun Xiaoning Du Fu Song Shangwen Wang Li Li Beihang University Beijing China Monash University Melbourne Victoria Australia State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China National University of Defense Technology Changsha China Beijing Yunnan Key Laboratory of Software Engineering Beihang University China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

Leveraging recent advancements in large language models, modern neural code completion models have demonstrated the capability to generate highly accurate code suggestions. However, their massive size poses challenges in terms of computational costs and environmental impact, hindering their widespread adoption in practical scenarios. Dynamic inference emerges as a promising solution, as it allocates minimal computation during inference while maintaining the model's performance. In this research, we explore dynamic inference within the context of code completion. Initially, we conducted an empirical investigation on GPT-2, focusing on the inference capabilities of intermediate layers for code completion. We found that 54.4% of tokens can be accurately generated using just the first layer, signifying significant computational savings potential. Moreover, despite using all layers, the model still fails to predict 14.5% of tokens correctly, and the subsequent completions continued from them are rarely considered helpful, with only a 4.2% Acceptance Rate. These findings motivate our exploration of dynamic inference in code completion and inspire us to enhance it with a decision-making mechanism that stops the generation of incorrect code. We thus propose a novel dynamic inference method specifically tailored for code completion models. This method aims not only to produce correct predictions with largely reduced computation but also to prevent incorrect predictions proactively. Our extensive evaluation shows that it can averagely skip 1.7 layers out of 16 layers in the models, leading to an 11.2% speedup with only a marginal 1.1 % reduction in ROUGE- L.

关键词： Codes Accuracy Computational modeling Decision making Focusing Predictive models Dynamic scheduling

来源：评论

学校读者我要写书评

暂无评论

Anomaly Handwritten Text Detection for Automatic Descriptive Answer Evaluation 22

Anomaly Handwritten Text Detection for Automatic Descriptive...

引用

Proceedings of the 2022 11th International Conference on Computing and Pattern Recognition

作者： Nilanjana Chatterjee Palaiahnaakote Shivakumara Umapada Pal Tong Lu Yue Lu Computer Vision and Pattern Recognition Unit Indian Statistical Institute India Faculty of Computer Science and Information Technology University of Malaya Malaysia National Key Lab for Novel Software Technology Nanjing University China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University China

ISBN: (纸本)9781450397056

Although there are advanced technologies for character recognition, automatic descriptive answer evaluation is an open challenge for the document image analysis community due to large diversified handwritten text and answers to the question. This paper presents a novel method for detecting anomaly handwritten text in the responses written by the students to the questions. The method is proposed based on the fact that when the students are confident in answering questions, the students usually write answers legibly and neatly while they are not confident, they write sloppy writing which may not be easy for the reader to understand. To detect such anomaly handwritten text, we explore a new combination of Fourier transform and deep learning model for detecting edges. This result preserves the structure of handwritten text. For extracting features for classification of anomaly text and normal text, the proposed method studies the behavior of writing style, especially the variation at ascenders and descenders. Therefore, the proposed work draws principal axis which is invariant to rotation, scaling and some extent to distortion for the edge images. With respect to principal axis, the proposed method draws medial axis using uppermost and lowermost points. The distance between the medial axis and principal axis points are considered as feature vector. Further, the feature vector is passed to Artificial Neural Network for classification of anomaly text. The proposed method is evaluated by testing on our own dataset, standard dataset of gender identification (IAM) and handwritten forgery detection dataset (ACPR 2019). The results on different datasets show that the proposed work outperforms the existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Testing Database Systems via Differential Query Execution

Testing Database Systems via Differential Query Execution

引用

International Conference on software Engineering (ICSE)

作者： Jiansen Song Wensheng Dou Ziyu Cui Qianwang Dai Wei Wang Jun Wei Hua Zhong Tao Huang State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences University of Chinese Academy of Sciences Nanjing College Nanjing Institute of Software Technology

Database Management Systems (DBMSs) provide efficient data retrieval and manipulation for many applications through Structured Query Language (SQL). Incorrect implementations of DBMSs can result in logic bugs, which cause SELECT queries to fetch incorrect results, or UPDATE and DELETE queries to generate incorrect database states. Existing approaches mainly focus on detecting logic bugs in SELECT queries. However, logic bugs in UPDATE and DELETE queries have not been tackled. In this paper, we propose a novel and general approach, which we have termed Differential Query Execution (DQE), to detect logic bugs in SELECT, UPDATE and DELETE queries of DBMSs. The core idea of DQE is that different SQL queries with the same predicate usually access the same rows in a database. For example, a row updated by an UPDATE query with a predicate φ should also be fetched by a SELECT query with the same predicate φ, If not, a logic bug is revealed in the target DBMS. To evaluate the effectiveness and generality of DQE, we apply DQE on five production-level DBMSs, i.e., MySQL, MariaDB, TiDB, CockroachDB and SQLite. In total, we have detected 50 unique bugs in these DBMSs, 41 of which have been confirmed, and 11 have been fixed. We expect that the simplicity and generality of DQE can greatly improve the reliability of DBMSs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Adversarial Robustness via Feature Pattern Consistency Constraint

arXiv

引用

arXiv 2024年

作者： Hu, Jiacong Ye, Jingwen Feng, Zunlei Yang, Jiazhen Liu, Shunyu Yu, Xiaotian Jia, Lingxiang Song, Mingli College of Computer Science and Technology Zhejiang University China School of Software Technology Zhejiang University China State Key Laboratory of Blockchain and Security Zhejiang University China Institute of Blockchain and Data Security China National University of Singapore Singapore

Convolutional Neural Networks (CNNs) are well-known for their vulnerability to adversarial attacks, posing significant security concerns. In response to these threats, various defense methods have emerged to bolster the model’s robustness. However, most existing methods either focus on learning from adversarial perturbations, leading to overfitting to the adversarial examples, or aim to eliminate such perturbations during inference, inevitably increasing computational burdens. Conversely, clean training, which strengthens the model’s robustness by relying solely on clean examples, can address the aforementioned issues. In this paper, we align with this methodological stream and enhance its generalizability to unknown adversarial examples. This enhancement is achieved by scrutinizing the behavior of latent features within the network. Recognizing that a correct prediction relies on the correctness of the latent feature’s pattern, we introduce a novel and effective Feature Pattern Consistency Constraint (FPCC) method to reinforce the latent feature’s capacity to maintain the correct feature pattern. Specifically, we propose Spatial-wise Feature Modification and Channel-wise Feature Selection to enhance latent features. Subsequently, we employ the Pattern Consistency Loss to constrain the similarity between the feature pattern of the latent features and the correct feature pattern. Our experiments demonstrate that the FPCC method empowers latent features to uphold correct feature patterns even in the face of adversarial examples, resulting in inherent adversarial robustness surpassing state-of-the-art models. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Long- and Short- Term Sequential Recommendation with Temporal Interval

Long- and Short- Term Sequential Recommendation with Tempora...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Kun He Qiyan Liu Qianmu Li Shunmei Meng Nanjing University of Science and Technology Nanjing China Computer Engineering University of Toronto State Key Lab. for Novel Software Technology Nanjing University Nanjing China

Sequential recommendation aims to learn the changes of users’ interests according to their historical behaviors and predict the most likely next item. Since user’s historical behavior are sequential actions, user’s interest in different time periods has different emphases. For predicting a user’s next item, not only the recent behavior is important, but also long-term preference with all historical behaviors could not be ignored. Recently, self-attention based user preference modeling has drawn much attention for its advantages of fewer parameters and parallelism. However, most of the existing self-attention based model do not make a good distinction between the long-term and short-term preferences of users. Based on the observations, we design a sequential recommendation model based on a combination of long-term and short-term preference. On the one hand, considering the changes of users’ interests in different periods, we divide the sequence of users’ behaviors into different temporal windows. Then, we use GRU to capture users’ interests in different temporal window. On the other hand, to better combine the global and local information of user’s, we adopt a locally constrained multi-head attention mechanism based on Transformer encoder. On three real-world public datasets, we finally validate the efficacy of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploit your Latents: Coarse-Grained Protein Backmapping with Latent Diffusion Models 39

Exploit your Latents: Coarse-Grained Protein Backmapping wit...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Rongchao Huang, Yu Lou, Yiwei Xin, Yi Chen, Haixu Cao, Yongzhi Wang, Hanpin Key Laboratory of High Confidence Software Technologies Peking University Ministry of Education School of Computer Science Peking University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Institute of Geriatrics National Clinical Research Center of Geriatrics Disease Chinese PLA General Hospital Beijing China

ISBN: (纸本)157735897X

Coarse-grained (CG) molecular dynamics of proteins is a preferred approach to studying large molecules on extended time scales by condensing the entire atomic model into a limited number of pseudo-atoms and preserving the thermodynamic properties of the system. However, the significantly increased efficiency impedes the analysis of substantial physicochemical information, since high-resolution atomic details are sacrificed to accelerate simulation. In this paper, we propose LatCPB, a generative approach based on diffusion that enables high-resolution backmapping of CG proteins. Specifically, our model encodes an all-atom into discrete latent embeddings, aligned with learnable multimodal discrete priors for circumventing posterior collapse and maintaining the discrete properties of the protein sequence. During the generation, we further design a latent diffusion process within the continuous latent space due to the potential stochastics in the data. Moreover, LatCPB performs a contrastive learning strategy in latent space to separate feature representations of various molecules and conformations of the same molecule, thus enhancing the comprehension of molecular representational diversity. Experimental results demonstrate that LatCPB is able to backmap CG proteins effectively and achieve outstanding performance. © 2025, Association for the Advancement of Artificial Intelligence (***). 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

Physics-informed Inverse Design of Multi-bit Programmable Metasurfaces

arXiv

引用

arXiv 2024年

作者： Xu, Yucheng Yang, Jia-Qi Fan, Kebin Wang, Sheng Wu, Jingbo Zhang, Caihong Zhan, De-Chuan Padilla, Willie J. Jin, Biaobing Chen, Jian Wu, Peiheng Key Laboratory of Optoelectronic Devices and Systems with Extreme Performances of MOE School of Electronic Science and Engineering Nanjing University Nanjing210023 China Purple Mountain Laboratories Nanjing211111 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China Department of Electrical and Computer Engineering Duke University Box 90291 DurhamNC27708 United States

Emerging reconfigurable metasurfaces offer various possibilities in programmatically manipulating electromagnetic waves across spatial, spectral, and temporal domains, showcasing great potential for enhancing terahertz applications. However, they are hindered by limited tunability, particularly evident in relatively small phase tuning over 270o, due to the design constraints with time-intensive forward design methodologies. Here, we demonstrate a multi-bit programmable metasurface capable of terahertz beam steering, facilitated by a developed physics-informed inverse design (PIID) approach. Through integrating a modified coupled mode theory (MCMT) into residual neural networks, our PIID algorithm not only significantly increases the design accuracy compared to conventional neural networks but also elucidates the intricate physical relations between the geometry and the modes. Without decreasing the reflection intensity, our method achieves the enhanced phase tuning as large as 300o. Additionally, we experimentally validate the inverse designed programmable beam steering metasurface, which is adaptable across 1-bit, 2-bit, and tri-state coding schemes, yielding a deflection angle up to 68o and broadened steering coverage. Our demonstration provides a promising pathway for rapidly exploring advanced metasurface devices, with potentially great impact on communication and imaging technologies. © 2024, CC0.

关键词： Tuning

来源：评论

学校读者我要写书评

暂无评论

Learning the Relation between Similarity Loss and Clustering Loss in Self-Supervised Learning

arXiv

引用

arXiv 2023年

作者： Ge, Jidong Liu, Yuxiang Gui, Jie Fang, Lanting Lin, Ming Kwok, James Tin-Yau Huang, LiGuo Luo, Bin State Key Laboratory for Novel Software Technology Software Institute Nanjing University Nanjing210093 China The School of Cyber Science and Engineering Southeast University Purple Mountain Laboratories Nanjing210000 China *** L.L.C. United States Alibaba Group China The Department of Computer Science and Engineering The Hong Kong University of Science and Technology 999077 Hong Kong The Department of Computer Science Southern Methodist University DallasTX75205 United States

Self-supervised learning enables networks to learn discriminative features from massive data itself. Most state-of-the-art methods maximize the similarity between two augmentations of one image based on contrastive learning. By utilizing the consistency of two augmentations, the burden of manual annotations can be freed. Contrastive learning exploits instance-level information to learn robust features. However, the learned information is probably confined to different views of the same instance. In this paper, we attempt to leverage the similarity between two distinct images to boost representation in self-supervised learning. In contrast to instance-level information, the similarity between two distinct images may provide more useful information. Besides, we analyze the relation between similarity loss and feature-level cross-entropy loss. These two losses are essential for most deep learning methods. However, the relation between these two losses is not clear. Similarity loss helps obtain instance-level representation, while feature-level cross-entropy loss helps mine the similarity between two distinct images. We provide theoretical analyses and experiments to show that a suitable combination of these two losses can get state-of-the-art results. Code is available at https://***/guijiejie/ICCL. Copyright © 2023, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

HMGS:Hierarchical Matching Graph Neural Network for Session-Based Recommendation

引用

computers, Materials & Continua 2025年第6期83卷 5413-5428页

作者： Pengfei Zhang Rui Xin Xing Xu Yuzhen Wang Xiaodong Li Xiao Zhang Meina Song Zhonghong Ou State Grid Hebei Information and Telecommunication Branch Shijiazhuang050000China School of Computer Science(National Pilot Software Engineering School) Beijing University of Posts and TelecommunicationsBeijing100876China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and TelecommunicationsBeijing100876China

Session-based recommendation systems(SBR)are pivotal in suggesting items by analyzing anonymized sequences of user *** methods,while competent,often fall short in two critical areas:they fail to address potential inter-session item transitions,which are behavioral dependencies that extend beyond individual session boundaries,and they rely on monolithic item aggregation to construct session *** approach does not capture the multi-scale and heterogeneous nature of user intent,leading to a decrease in modeling *** overcome these limitations,a novel approach called HMGS has been *** system incorporates dual graph architectures to enhance the recommendation process.A global transition graph captures latent cross-session item dependencies,while a heterogeneous intra-session graph encodesmulti-scale item embeddings through localized feature ***,amulti-tier graphmatchingmechanism aligns user preference signals across different granularities,significantly improving interest localization *** validation on benchmark datasets(Tmall and Diginetica)confirms HMGS’s efficacy against state-of-the-art *** analysis reveals performance gains of 20.54%and 12.63%in Precision@10 on Tmall and Diginetica,*** improvements are observed across auxiliary metrics,with MRR@10,Precision@20,and MRR@20 exhibiting enhancements between 4.00%and 21.36%,underscoring the framework’s robustness in multi-faceted recommendation scenarios.

关键词： Session-based recommendation graph network multi-level matching

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attacks on Large Language Model-Based System and Mitigating Strategies: A Case Study on ChatGPT

引用

Security and Communication Networks 2023年第1期2023卷

作者： Liu, Bowen Xiao, Boao Jiang, Xutong Cen, Siyuan He, Xin Dou, Wanchun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Guangdong Laboratory of Artificial Intelligence and Digital Economy Shenzhen China School of Computer Science & Technology Nanjing University of Posts and Telecommunications Nanjing China College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China

Machine learning algorithms are at the forefront of the development of advanced information systems. The rapid progress in machine learning technology has enabled cutting-edge large language models (LLMs), represented by GPT-3 and ChatGPT, to perform a wide range of NLP tasks with a stunning performance. However, research on adversarial machine learning highlights the need for these intelligent systems to be more robust. Adversarial machine learning aims to evaluate attack and defense mechanisms to prevent the malicious exploitation of these systems. In the case of ChatGPT, adversarial induction prompt can cause the model to generate toxic texts that could pose serious security risks or propagate false information. To address this challenge, we first analyze the effectiveness of inducing attacks on ChatGPT. Then, two effective mitigating mechanisms are proposed. The first is a training-free prefix prompt mechanism to detect and prevent the generation of toxic texts. The second is a RoBERTa-based mechanism that identifies manipulative or misleading input text via external detection models. The availability of this method is demonstrated through experiments. © 2023 Bowen Liu et al.

关键词： Machine learning

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：