检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Fu, Weiping Wei, Bifan Hu, Jianxiang Cai, Zhongmin Liu, Jun School of Computer Science and Technology Xi'an Jiaotong University Xi'an China School of Continuing Education Xi'an Jiaotong University Xi'an China MOE KLINNS Lab School of Automation Science and Engineering Xi'an Jiaotong University Xi'an China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an China

ISBN: (纸本)9798891761643

Automatically generated questions often suffer from problems such as unclear expression or factual inaccuracies, requiring a reliable and comprehensive evaluation of their quality. Human evaluation is widely used in the field of question generation (QG) and serves as the gold standard for automatic metrics. However, there is a lack of unified human evaluation criteria, which hampers consistent and reliable evaluations of both QG models and automatic metrics. To address this, we propose QGEval, a multi-dimensional Evaluation benchmark for Question Generation, which evaluates both generated questions and existing automatic metrics across 7 dimensions: fluency, clarity, conciseness, relevance, consistency, answerability, and answer consistency. We demonstrate the appropriateness of these dimensions by examining their correlations and distinctions. Through consistent evaluations of QG models and automatic metrics with QGEval, we find that 1) most QG models perform unsatisfactorily in terms of answerability and answer consistency, and 2) existing metrics fail to align well with human judgments when evaluating generated questions across the 7 dimensions. We expect this work to foster the development of both QG technologies and their evaluation. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

xGCN: An Extreme Graph Convolutional Network for Large-scale Social Link Prediction 23

xGCN: An Extreme Graph Convolutional Network for Large-scale...

引用

2023 World Wide Web Conference, WWW 2023

作者： Song, Xiran Lian, Jianxun Huang, Hong Luo, Zihan Zhou, Wei Lin, Xue Wu, Mingqi Li, Chaozhuo Xie, Xing Jin, Hai Huazhong University of Science and Technology Wuhan China Microsoft Research Asia Beijing China Microsoft Gaming Redmond United States National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9781450394161

Graph neural networks (GNNs) have seen widespread usage across multiple real-world applications, yet in transductive learning, they still face challenges in accuracy, efficiency, and scalability, due to the extensive number of trainable parameters in the embedding table and the paradigm of stacking neighborhood aggregations. This paper presents a novel model called xGCN for large-scale network embedding, which is a practical solution for link predictions. xGCN addresses these issues by encoding graph-structure data in an extreme convolutional manner, and has the potential to push the performance of network embedding-based link predictions to a new record. Specifically, instead of assigning each node with a directly learnable embedding vector, xGCN regards node embeddings as static features. It uses a propagation operation to smooth node embeddings and relies on a Refinement neural Network (RefNet) to transform the coarse embeddings derived from the unsupervised propagation into new ones that optimize a training objective. The output of RefNet, which are well-refined embeddings, will replace the original node embeddings. This process is repeated iteratively until the model converges to a satisfying status. Experiments on three social network datasets with link prediction tasks show that xGCN not only achieves the best accuracy compared with a series of competitive baselines but also is highly efficient and scalable. © 2023 ACM.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Leverage Learning Behaviour data for Students' Learning Performance Prediction and Influence Factor Analysis

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2422-2433页

作者： Ni, Qin Zhu, Yanjin Zhang, Lingying Lu, Xiaochen Zhang, Lei Shanghai International Studies University Key Laboratory of Multilingual Education with AI Shanghai201620 China Donghua University College of Information Science and Technology Shanghai201620 China Donghua University Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education Shanghai201620 China Shanghai Normal University Shanghai Engineering Research Center of Intelligent Education and Bigdata and Lab for Educational Big Data and Policymaking Shanghai200234 China

Online education has become increasingly significant for university students and faculty, especially in the context of the modern remote education landscape. However, the inherent space-time separation in online education can create communication delays between teachers and students, making it challenging to monitor students' behaviors effectively. In an effort to understand the connection between students' online engagement and their learning performance, data annotation has been implemented to address the issue of accurately representing students' learning behaviors. Taking the online teaching data of Shanghai Normal University platform as the research object, the primary online education problem is explored through data mining, which includes correlation analysis, Gini importance ranking, and principal component analysis (PCA). Then, constructing the learning performance prediction model using random forest (RF) based on PCA by comparing various machine learning algorithms. As a consequence, the most influential online learning behaviors are course duration time, document learning time, test average score, and video completion rate. The overall classification accuracy of the learning performance prediction model is 87.45%, and the highest prediction accuracy for a single category is 96.52%. © 2020 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Electric Energy Charge Biclustering A Genetic Algorithms Approach

Electric Energy Charge Biclustering A Genetic Algorithms App...

引用

CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON)

作者： Josué Trepowski P. Pinto-Roa Diego García-Torres Miguel Federico Divina Facultad Politécnica Universidad Nacional de Asunción San Lorenzo Paraguay Data Science and Big Data Lab Pablo de Olavide University Seville Spain

The increased usage of Electric Vehicles (EV) due to the transition from fossil fuels to clean energy sources presents the challenge of integrating EV charging into the electrical grid, leading to the analysis of charging patterns for decision-making. This document proposes an evolutionary biclustering algorithm which main objective is to find EV charging patterns in a time series. The algorithm has been tested with real-life data. Our numerical simulation results proved that our algorithm is able to identify concurrent peak usage in different regions in big time intervals. This new technique can be used to avoid creation of new voltage peak and energy loss while integrating EV charge infrastructure into the current electrical grid.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Fine-Tuning based Backdoor Defense with Sharpness-Aware Minimization

Enhancing Fine-Tuning based Backdoor Defense with Sharpness-...

引用

International Conference on Computer Vision (ICCV)

作者： Mingli Zhu Shaokui Wei Li Shen Yanbo Fan Baoyuan Wu School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen (CUHK-Shenzhen) China JD Explore Academy Tencent AI Lab

Backdoor defense, which aims to detect or mitigate the effect of malicious triggers introduced by attackers, is becoming increasingly critical for machine learning security and integrity. Fine-tuning based on benign data is a natural defense to erase the backdoor effect in a backdoored model. However, recent studies show that, given limited benign data, vanilla fine-tuning has poor defense performance. In this work, we firstly investigate the vanilla fine-tuning process for backdoor mitigation from the neuron weight perspective, and find that backdoor-related neurons are only slightly perturbed in the vanilla fine-tuning process, which explains its poor backdoor defense performance. To enhance the fine-tuning based defense, inspired by the observation that the backdoor-related neurons often have larger weight norms, we propose FT-SAM, a novel backdoor defense paradigm that aims to shrink the norms of backdoor-related neurons by incorporating sharpness-aware minimization with fine-tuning. We demonstrate the effectiveness of our method on several benchmark datasets and network architectures, where it achieves state-of-the-art defense performance, and provide extensive analysis to reveal the FT-SAM’s mechanism. Overall, our work provides a promising avenue for improving the robustness of machine learning models against backdoor attacks. Codes are available at https://***/SCLBD/BackdoorBench.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LLGS: Illuminating Gaussian Splatting via absorptance Modulation

LLGS: Illuminating Gaussian Splatting via absorptance Modula...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Gan, Jianwen Li, Wenxin Zheng, Bo Wang, Chengliang Wu, Yingbo National Elite Institute of Engineering Chongqing University Chongqing China AI Lab Chongqing Changan Automobile Co. Ltd. Chongqing China College of Computer Science Chongqing University Chongqing China School of Big Data & Software Engineering Chongqing University Chongqing China

ISBN: (纸本)9798350368741

Low-light images are typically characterized by low pixel intensity and color distortion, presenting a significant challenge for accurate 3D reconstruction with 3D Gaussian Splatting (3DGS). Traditional 2D enhancement methods fail to maintain consistent illumination, affecting reconstruction quality. We propose Low-Light Gaussian (LLGS), which can directly leverage low-light images for 3D reconstruction and synthesizing normal-light novel views. LLGS incorporates absorptance to simulate light behavior in low-light conditions, assuming objects maintain normal illumination while reflected light intensity attenuates due to absorptance during rendering. This approach enables the capture of authentic color information in dimly lit scenes. LLGS outperforms current enhancement algorithms and Neural Radiance Fields (NeRF) in image quality and processing efficiency, making it highly effective for low-light 3D scene reconstruction and novel view synthesis. © 2025 IEEE.

关键词： 3D gaussians Low-light image enhancement Novel view synthesis Radiance fields

来源：评论

学校读者我要写书评

暂无评论

MOLECULE GENERATION FOR TARGET PROTEIN BINDING WITH STRUCTURAL MOTIFS 11

MOLECULE GENERATION FOR TARGET PROTEIN BINDING WITH STRUCTUR...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Zhang, Zaixi Min, Yaosen Zheng, Shuxin Liu, Qi Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Institute of Interdisciplinary Information Sciences Tsinghua University China Microsoft Research United States

Designing ligand molecules that bind to specific protein binding sites is a fundamental problem in structure-based drug design. Although deep generative models and geometric deep learning have made great progress in drug design, existing works either sample in the 2D graph space or fail to generate valid molecules with realistic substructures. To tackle these problems, we propose a Fragment-based LigAnd Generation framework (FLAG), to generate 3D molecules with valid and realistic substructures fragment-by-fragment. In FLAG, a motif vocabulary is constructed by extracting common molecular fragments (i.e., motif) in the dataset. At each generation step, a 3D graph neural network is first employed to encode the intermediate context information. Then, our model selects the focal motif, predicts the next motif type, and attaches the new motif. The bond lengths/angles can be quickly and accurately determined by cheminformatics tools. Finally, the molecular geometry is further adjusted according to the predicted rotation angle and the structure refinement. Our model not only achieves competitive performances on conventional metrics such as binding affinity, QED, and SA, but also outperforms baselines by a large margin in generating molecules with realistic substructures. Our code is publicly available at https://***/zaixizhang/FLAG. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

RefXVC: Cross-Lingual Voice Conversion with Enhanced Reference Leveraging

arXiv

引用

arXiv 2024年

作者： Zhang, Mingyang Zhou, Yi Ren, Yi Zhang, Chen Yin, Xiang Li, Haizhou The Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen China The Department of Electrical and Computer Engineering National University of Singapore Singapore Speech & Audio Team ByteDance AI Lab

This paper proposes RefXVC, a method for cross-lingual voice conversion (XVC) that leverages reference information to improve conversion performance. Previous XVC works generally take an average speaker embedding to condition the speaker identity, which does not account for the changing timbre of speech that occurs with different pronunciations. To address this, our method uses both global and local speaker embeddings to capture the timbre changes during speech conversion. Additionally, we observed a connection between timbre and pronunciation in different languages and utilized this by incorporating a timbre encoder and a pronunciation matching network into our model. Furthermore, we found that the variation in tones is not adequately reflected in a sentence, and therefore, we used multiple references to better capture the range of a speaker’s voice. The proposed method outperformed existing systems in terms of both speech quality and speaker similarity, highlighting the effectiveness of leveraging reference information in cross-lingual voice conversion. The converted speech samples can be found on the website: http://*** © 2024, CC BY-NC-SA.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

On-Line System of Garbage Image-Orientated Intelligent Classification, Submission and Examination

On-Line System of Garbage Image-Orientated Intelligent Class...

引用

IEEE International Conference on e-Business Engineering (ICEBE)

作者： Jiayin Tian Yaozhi Wang Jiaxin Liu Yan Chen School of Computer Science and Technology Xi'an Jiaotong University Xi'an Shaanxi China Shaanxi Key Lab of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an Shaanxi China Shaanxi Key Lab of Big Data Knowledge Engineering School of Computer Science and Technology Xi'an Jiaotong University Xi'an Jiaotong University Xi'an Shaanxi China

ISBN: (数字)9798350365856

ISBN: (纸本)9798350365863

In a world brimming with new products continually, novel waste types are ubiquitous. This makes current image-based garbage classification systems difficult to perform well due to the long-tailed effects of distribution of garbage types, and necessitates an urgent and efficient garbage classification with abilities of detecting new and rare wastes and class-incremental learning for environmental sustainability. Therefore, we propose a framework of Online System of Garbage Image-Oriented Intelligent Classification, Submission, and Examination, facilitating the incremental garbage classification efforts. In which, to identify novel garbage effectively, we also introduced few-shot object detection method with two key algorithms: Two-Stage Object Detection Learning Algorithm and Dynamic Query-based Incremental Few-shot Learning Algorithm. Our experiment results show that Both outperform the current existing ones in dataset, MS COCO. Then, a strategy of Class-Incremental learning based Residual Network is proposed to meet the need of new waste class-incremental learning. The experimental results support our strategy. Finally, a prototype system employed the above algorithms and the strategy is described.

关键词： Image recognition Heavily-tailed distribution Heuristic algorithms Green products Prototypes Object detection Classification algorithms Object recognition Few shot learning Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

DarkSAM: fooling segment anything model to segment nothing 24

DarkSAM: fooling segment anything model to segment nothing

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Ziqi Zhou Yufei Song Minghui Li Shengshan Hu Xianlong Wang Leo Yu Zhang Dezhong Yao Hai Jin National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Cluster and Grid Computing Lab and School of Computer Science and Technology Huazhong University of Science and Technology School of Cyber Science and Engineering Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security and School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (纸本)9798331314385

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM. Our codes are available at: https://***/CGCL-codes/DarkSAM.

关键词：

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：