检索结果-内蒙古大学图书馆

International Conference on data Engineering

作者： Junkang Wu Jiawei Chen Jiancan Wu Wentao Shi Jizhi Zhang Xiang Wang MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition University of Science and Technology of China Hefei China The State Key Laboratory of Blockchain and Data Security Zhejiang Unversity

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Loss functions steer the optimization direction of recommendation models and are critical to model performance, but have received relatively little attention in recent recommendation research. Among various losses, we find Softmax loss (SL) stands out for not only achieving remarkable accuracy but also better robustness and fairness. Nevertheless, the current literature lacks a comprehensive explanation for the efficacy of SL. Toward addressing this research gap, we conduct theoretical analyses on SL and uncover three insights: 1) Optimizing SL is equivalent to performing Distributionally Robust Optimization (DRO) on the negative data, thereby learning against perturbations on the negative distribution and yielding robustness to noisy negatives. 2) Comparing with other loss functions, SL implicitly penalizes the prediction variance, resulting in a smaller gap between predicted values and and thus producing fairer results. Building on these insights, we further propose a novel loss function Bilateral SoftMax Loss (BSL) that extends the advantage of SL to both positive and negative sides. BSL augments SL by applying the same Log-Expectation-Exp structure to positive examples as is used for negatives, making the model robust to the noisy positives as well. Remarkably, BSL is simple and easy-to-implement - requiring just one additional line of code compared to SL. Experiments on four real-world datasets and three representative backbones demonstrate the effectiveness of our proposal. The code is available at https://***/junkangwu/BSL.

关键词： Codes Accuracy Perturbation methods data engineering Robustness Noise measurement Proposals

来源：评论

学校读者我要写书评

暂无评论

Sustainability Forecasting for Deep Learning Packages 31

Sustainability Forecasting for Deep Learning Packages

引用

31st IEEE International Conference on Software Analysis, Evolution and Reengineering, SANER 2024

作者： Han, Junxiao Wang, Yunkun Liu, Zhongxin Bao, Lingfeng Liu, Jiakun Lo, David Deng, Shuiguang School of Computer & Computing Science Hangzhou City University Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China School of Computing and Information Systems Singapore Management University Singapore Singapore

ISBN: (纸本)9798350330663

Deep Learning (DL) technologies have been widely adopted to tackle various tasks. In this process, through software dependencies, a multi-layer DL supply chain (SC) is formed, with DL frameworks acting as the root, DL packages acting as the bridge nodes, and downstream DL projects acting as the periphery. However, most Open Source Software (OSS) projects may fail. Considering the crucial position of DL packages in the DL SC, to foster the sustainable development of DL SCs and DL packages, we aim to forecast the long-term sustainability of DL packages. Here, sustained activity is adopted as the main proxy of sustainability, and the sustainability status is classified as 'sus-tainable' or 'dormant'. Relatedly, a DL package is considered as 'sustainable' if it has sustained activity in its last 12 months. Otherwise, it is deemed as 'dormant'. To this end, we propose an approach that begins with obtaining longitudinal features for each DL package in each month. Then, we develop a model to forecast the sustainability of DL packages by incorporating the longitudinal features, which can aptly predict sustainability with an accuracy of up to 0.81. Subsequently, an interpretable module is developed to interpret the determinants (i.e., important features) that impact the sustainability of DL packages. Finally, we generate sustainability trajectories for each DL package to better understand the monthly changes of their sustainability status. Our findings uncover that for most DL packages, fewer but more centralized developers and a balanced collaboration are more likely to help sustain the DL packages. Furthermore, although some DL packages are sustainable, their sustainability trajectories present statistically decreasing trends over time. Based on the findings, we shed light on the dynamic sustainability of DL packages, highlight future research directions, and provide practical suggestions to DL package maintainers, developers, users, and software engineering researchers. ©

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Distinguishing LLM-generated from Human-written Code by Contrastive Learning

arXiv

引用

arXiv 2024年

作者： Xu, Xiaodan Ni, Chao Guo, Xinrong Liu, Shaoxuan Wang, Xiaoya Liu, Kui Yang, Xiaohu State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Software Engineering Application Technology Lab Huawei Hangzhou China

Large language models (LLMs), such as ChatGPT released by OpenAI, have attracted significant attention from both industry and academia due to their demonstrated ability to generate high-quality content for various tasks. Despite the impressive capabilities of LLMs, there are growing concerns regarding their potential risks in various fields, such as news, education, and software engineering. Recently, several commercial and open-source LLM-generated content detectors have been proposed, which, however, are primarily designed for detecting natural language content without considering the specific characteristics of program code. This paper aims to fill this gap by proposing a novel ChatGPT-generated code detector, CodeGPTSensor, based on a contrastive learning framework and a semantic encoder built with UniXcoder. To assess the effectiveness of CodeGPTSensor on differentiating ChatGPT-generated code from human-written code, we first curate a large-scale Human and Machine comparison Corpus (HMCorp), which includes 550K pairs of human-written and ChatGPT-generated code (i.e., 288K Python code pairs and 222K Java code pairs). Based on the HMCorp dataset, our qualitative and quantitative analysis of the characteristics of ChatGPT-generated code reveals the challenge and opportunity of distinguishing ChatGPT-generated code from human-written code with their representative features. Our experimental results indicate that CodeGPTSensor can effectively identify ChatGPT-generated code, outperforming all selected baselines. 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

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

Hierarchical Local Global Transformer for Point Clouds Analysis

SSRN

引用

SSRN 2023年

作者： Li, Dilong Zheng, Shenghong Chen, Ziyi Li, Xiang Wang, Lanying Du, Jixiang College of Computer Science and Technology Fujian Key Laboratory of Big Data Intelligence and Security Xiamen Key Laboratory of Computer Vision and Pattern Recognition Xiamen Key Laboratory of Data Security and Blockchain Technology Huaqiao University FJ Xiamen361021 China School of Economics and Finance Huaqiao University FJ Quanzhou362021 China Department of Geography and Environmental Management University of Waterloo WaterlooONN2L 3G1 Canada

Transformer networks have demonstrated remarkable performance in point cloud analysis. However, achieving a balance between local regional context and global long-range context learning remains a significant challenge. In this paper, we propose a Hierarchical Local Global Transformer Network (LGTNet), designed to capture local and global contexts in a hierarchical manner. Specifically, we employ serial local and global Transformers to learn the inner-group and cross-group self-attention, respectively. Besides, we propose a geometric moment-based position encoding for local Transformer, enabling the embedding of comprehensive local geometric relationship. Additionally, we also introduce a global feature pooling module that extracts the global features from each encoder layers. Extensive experimental results demonstrate that LGTNet achieves state-of-the-art performance on ShapeNetPart and ScanObjectNN datasets. This approach effectively enhances the understanding of point cloud scenes, thereby facilitating the use of point cloud data in remote sensing applications. © 2023, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

K-CIRCT: A Layered, Composable, and Executable Formal Semantics for CIRCT Hardware IRs

arXiv

引用

arXiv 2024年

作者： Zhao, Jianhong Kang, Jinhui Zhao, Yongwang School of Cyber Science and Technology College of Computer Science and Technology Zhejiang University China State Key Laboratory of Blockchain and Data Security Zhejiang University China

CIRCT, an open-source EDA framework akin to LLVM for software, is a foundation for various hardware description languages. Despite its crucial role, CIRCT’s lack of formal semantics challenges necessary rigorous hardware verification. Thus, this paper introduces K-CIRCT, the first formal semantics in K for a substantial CIRCT subset adequate for simulating a RISC-V processor. Our semantics are structured into multiple layers: (1) MLIR static semantics, which covers fundamental MLIR concepts across domains;(2) CIRCT common semantics, featuring a generic hardware model that captures key hardware features across dialects;and (3) composable and extensible semantics for specific dialects, formalized individually using a unified approach. This approach has been applied to formalize CIRCT core dialects. We validated our semantics through full-rule coverage tests and assessed its practicality using the popular RISC-V hardware design, riscv-mini. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective

arXiv

引用

arXiv 2024年

作者： Lin, Siyi Gao, Chongming Chen, Jiawei Zhou, Sheng Hu, Binbin Feng, Yan Chen, Chun Wang, Can University of Science and Technology of China Hefei China Zhejiang University Hangzhou China Ant Group Hangzhou China State Key Laboratory of Blockchain and Data Security Zhejiang University China College of Computer Science and Technology Zhejiang University China Institute of Blockchain and Data Security China

Recommendation Systems (RS) are often plagued by popularity bias. When training a recommendation model on a typically long-tailed dataset, the model tends to not only inherit this bias but often exacerbate it, resulting in over-representation of popular items in the recommendation lists. This study conducts comprehensive empirical and theoretical analyses to expose the root causes of this phenomenon, yielding two core insights: 1) Item popularity is memorized in the principal spectrum of the score matrix predicted by the recommendation model;2) The dimension reduction phenomenon amplifies the relative prominence of the principal spectrum, thereby intensifying the popularity bias. Building on these insights, we propose a novel debiasing strategy that leverages a spectral norm regularizer to penalize the magnitude of the principal singular value. We have developed an efficient algorithm to expedite the calculation of the spectral norm by exploiting the spectral property of the score matrix. Extensive experiments across seven real-world datasets and three testing paradigms have been conducted to validate the superiority of the proposed method. Copyright © 2024, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Fast Query Answering by Labeling Index on Uncertain Graphs

Fast Query Answering by Labeling Index on Uncertain Graphs

引用

International Conference on data Engineering

作者： Zeyu Wang Qihao Shi Jiawei Chen Can Wang Mingli Song Xinyu Wang The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Hangzhou City University Hangzhou China Bangsun Technology Hangzhou China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Given the ubiquity of Uncertain Graphs (UGs), the field of UG mining has garnered increasing attention. Among various mining tasks, query processing stands out as the most fundamental and crucial. Current methods for query answering on UGs primarily rely on Monte-Carlo sampling and heuristic approaches. However, these techniques either struggle with a significant efficiency-accuracy trade-off or lack generalization over different graphs and queries. To circumvent these limitations, this work proposes a novel index-based method for query answering on UGs. We construct a labeling index framework, which can answer queries by pre-computed and stored operators. To the best of our knowledge, this is the first index frame-work that can deal with reliability, expected reliable distance and distance-constrained reliability queries, providing lower or upper bounded query answer results. By transferring the time consuming sampling process into the offline index operator computation, the query answering only needs to traverse a limited number of operators, which accelerates the response time of query answering with several orders of magnitude. We further utilize the vertex cover and its h-hop extension to prune the index structure, thereby reducing the space complexity. Experimental results on five real-world datasets demonstrate that the proposed index framework is both effective and efficient.

关键词： Monte Carlo methods Query processing data engineering Complexity theory Indexes Reliability Labeling

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT ONLINE LABEL CONSISTENT HASHING FOR LARGE-SCALE CROSS-MODAL RETRIEVAL

EFFICIENT ONLINE LABEL CONSISTENT HASHING FOR LARGE-SCALE CR...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Yi, Jinhan Liu, Xin Cheung, Yiu-Ming Xu, Xing Fan, Wentao He, Yi Department of Computer Science and Technology Huaqiao University Xiamen361021 China Xiamen Key Lab. of Computer Vision and Pattern Recognition Fujian Key Lab. of Big Data Intelligence and Security China Department of Computer Science Hong Kong Baptist University Kowloon Hong Kong School of Computer Science and Engineering University of Electronic Science and Technology of China China Provincial Key Laboratory for Computer Information Processing Technology Soochow University China

ISBN: (纸本)9781665438643

Existing cross-modal hashing still faces three challenges: (1) Most batch-based methods are unsuitable for processing large-scale and streaming data. (2) Current online methods often suffer from insufficient semantic association, while lacking flexibility to learn the hash functions for varying streaming data. (3) Existing supervised methods always require much computation time or accumulate large quantization loss to learn hash codes. To address above challenges, we present an efficient Online Label Consistent Hashing (OLCH) for cross-modal retrieval, which aims to incrementally learn hash codes for the current arriving data, while updating the hash functions at a streaming manner. To be specific, an online semantic representation learning framework is designed to adaptively preserve the semantic similarity across different modalities, and a mini-batch online gradient descent approach associated with forward-backward splitting is developed to optimize the hash functions. Accordingly, the hash codes are adaptively learned online with the high discriminative capability, while avoiding high computation complexity to process the streaming data. Experimental results show its outstanding performance in comparison with the-state-of-arts. © 2021 IEEE Computer Society. All rights reserved.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

A Novel Lexicon Enhanced Named Entity Recognition Model for Network security Domain

A Novel Lexicon Enhanced Named Entity Recognition Model for ...

引用

2024 China Automation Congress, CAC 2024

作者： Jin, Zhiyang Fu, Yusun Huan, Yuehui Xue, Jinliang Wang, Chengguang Chen, Yuanfang Ningbo Artificial Intelligence Institute Shanghai Jiao Tong University Ningbo China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Zhejiang Guoli Security Technology Co. Ltd Ningbo China Ningbo Industrial Internet Institute Ningbo China State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China

ISBN: (纸本)9798350368604

Named Entity Recognition (NER) technology serves as the foundation for solving many Natural Language Processing(NLP) problems, particularly in the domain of building knowledge graphs, where an effective NER model is crucial for creating efficient knowledge representations. However, when constructing knowledge graphs in the Industrial Internet security(IIS) domain, security-related incidents, as significant entities, pose challenges for existing NER models. In this paper, we propose security Lexicon Enhanced Bidirectional Encoder Representations from Transformers(SEBERT). SEBERT enhances semantic processing by integrating security lexicon information into one transformer layer of BERT, assigning vocabulary to each character in input sentences. Then we use a Residual-Knowledge-Arnold Network(RKAN) to optimize the semantic features learned from SEBERT, utilizing the properties of residual networks to learn identity mapping features without significantly increasing computational complexity. Finally, the Conditional Random Field (CRF) is used to learn the sequence information and dependencies of adjacent labels. Experimental results demonstrate that SEBERT-RKAN-CRF model achieves superior performance in recognizing entities in the IIS domain, with improvements of 1.99%, 3.34%, and 2.66% in accuracy rate, recall rate, and F1-score compared to the baseline model. © 2024 IEEE.

关键词： Semantics

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：