检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Chenxiao Yang Qitian Wu David Wipf Ruoyu Sun Junchi Yan School of Artificial Intelligence & Department of Computer Science and Engineering & MoE Lab of AI Shanghai Jiao Tong University Amazon Web Services School of Data Science The Chinese University of Hong Kong Shenzhen and Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data

A long-standing goal in deep learning has been to characterize the learning behavior of black-box models in a more interpretable manner. For graph neural networks (GNNs), considerable advances have been made in formalizing what functions they can represent, but whether GNNs will learn desired functions during the optimization process remains less clear. To fill this gap, we study their training dynamics in function space. In particular, we find that the gradient descent optimization of GNNs implicitly leverages the graph structure to update the learned function, as can be quantified by a phenomenon which we call kernel-graph alignment. We provide theoretical explanations for the emergence of this phenomenon in the overparameterized regime and empirically validate it on real-world GNNs. This finding offers new interpretable insights into when and why the learned GNN functions generalize, highlighting their limitations in heterophilic graphs. Practically, we propose a parameter-free algorithm that directly uses a sparse matrix (i.e. graph adjacency) to update the learned function. We demonstrate that this embarrassingly simple approach can be as effective as GNNs while being orders-of-magnitude faster.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Filtering Influential Features for Adolescent Positive Mental Health

Filtering Influential Features for Adolescent Positive Menta...

引用

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： Cao Yi Cai Shimin Zhou Tao Complex Lab University of Electronic Science and Technology of China Chengdu China Big Data Research Center University of Electronic Science and Technology of China Chengdu China

Adolescents' positive mental health is deeply associated with their growth. Identifying the factors that contribute to the positive mental health of junior and senior high school students is crucial for supporting youth development in the long run. Leveraging questionnaire data, this paper utilizes machine learning algorithms and fusion methods for feature selection to examine the factors that influence the onset of adolescent positive mental health. The influential features are ranked by importance. Then, machine learning algorithms in a heuristic form are employed to assess the predictive power of the fused features. The best f1-score of the classifiers reaches 0.844. It illustrates the effectiveness of feature filtering and provides valuable references for educational administrators to potential interventions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Course-Graph Discovery from Academic Performance Using Nonnegative LassoNet 18th

Course-Graph Discovery from Academic Performance Using Nonn...

引用

18th International Conference on Computer science and Education, ICCSE 2023

作者： Liu, Mengfei Wei, Shuangshuang Liu, Shuhui Shang, Xuequn Zhang, Yupei School of Computer Science Northwestern Polytechnical University Xi’an China MIIT Big Data Storage and Management Lab Xi’an China Department of Automation Tsinghua University Beijing China

ISBN: (纸本)9789819707362

This paper focuses on the problem of mining a course graph from students’ academic grades in formal education, which is an essential topic for artificial intelligence in education (AIED). However, most current methods often suffer from hardly understanding associations in practice. To this end, we formulate this problem into a feature selection schema that the proposed nonnegative LassoNet can solve. In the study case, we use the course scores of 4,577 records in the computer science department at our university. From the study results, our method achieves about 78% accuracy in score prediction with an acceptable error, which is better than traditional regression models with shrinkage. Based on the sparse self-expressive representation, we create a course map to show the associations behind the student’s academic performance, providing pieces of evidence for education studies and triggering exciting discoveries. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Football player identification based on YOLOv5 backbone and SPD-Conv 8

Football player identification based on YOLOv5 backbone and ...

引用

8th International Conference on Electronic Technology and Information science, ICETIS 2023

作者： Liu, Jiwei Li, Yanchao Ning, Tao Song, Jinmiao Duan, Xiaodong SEAC key Laboratory of Big Data Applied Technology Dalian Minzu University Dalian116000 China Dalian Key Lab of Digital Technology for National Culture Dalian Minzu University Dalian116600 China College of Computer Science and Engineering Dalian Minzu University Dalian116600 China

ISBN: (纸本)9781510666535

With the rapid development of computer technology and Internet technology, the information age has come. The combination of computer technology and sports is one of the most popular research fields. This paper mainly completes the construction of football player number dataset and identification of football players through the jersey number. Firstly, the dataset is constructed based on player detection and number region detection. Then in the player identification task, we uses part of the backbone network of YOLOv5 model as the feature extraction module of the player identification network. Moreover, SPD-Conv module is added to improve the network recognition performance under the condition of small size target and low resolution. A series of experiments were also done to verify the performance of our proposed model. Finally, the recognition accuracy of our proposed model reached 92.75%. © 2023 SPIE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

MISA: Unveiling the Vulnerabilities in Split Federated Learning

MISA: Unveiling the Vulnerabilities in Split Federated Learn...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wei Wan Yuxuan Ning Shengshan Hu Lulu Xue Minghui Li Leo Yu Zhang Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Computer Science and Technology Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University Cluster and Grid Computing Lab

Federated learning (FL) and split learning (SL) are prevailing distributed paradigms in recent years. They both enable shared global model training while keeping data localized on users’ devices. The former excels in parallel execution capabilities, while the latter enjoys low dependence on edge computing resources and strong privacy protection. Split federated learning (SFL) combines the strengths of both FL and SL, making it one of the most popular distributed architectures. Furthermore, a recent study has claimed that SFL exhibits robustness against poisoning attacks, with a fivefold improvement compared to FL in terms of *** this paper, we present a novel poisoning attack known as $\color{Fuchsia} {{\text{MISA}}}$. It poisons both the top and bottom models, causing a misalignment in the global model, ultimately leading to a drastic accuracy collapse. This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks. Extensive experiments demonstrate that our proposed MISA poses a significant threat to the availability of SFL, underscoring the imperative for academia and industry to accord this matter due attention.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RETIA: Relation-Entity Twin-Interact Aggregation for Temporal Knowledge Graph Extrapolation

RETIA: Relation-Entity Twin-Interact Aggregation for Tempora...

引用

International Conference on data Engineering

作者： Kangzheng Liu Feng Zhao Guandong Xu Xianzhi Wang Hai Jin 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 Wuhan China Data Science and Machine Intelligence Lab University of Technology Sydney Sydney Australia

Temporal knowledge graph (TKG) extrapolation aims to predict future unknown events (facts) based on historical information, and has attracted considerable attention due to its great practical significance. Accurate representations (embeddings) of entities and relations form the basis of TKG extrapolation. Recent work has been devoted to improving the rationality of entity representations. However, on the one hand, ignoring relation modeling results in incomplete relation representations; therefore, some approaches aggregate only immediately adjacent entities of relations, but this can lead to the "message islands" problem of relation modeling. On the other hand, ignoring the association constraints between relations and entities can make the embeddings of both relations and entities prone to overfitting. To address the abovementioned challenges, we propose an advanced method, namely, RETIA. For the former issue, we generate twin hyperrelation subgraphs for each historical subgraph and then aggregate both the adjacent entities and relations in the hyperrelation subgraphs through a graph convolutional network (GCN). About the latter concern, we propose a twin-interact module (TIM), which provides communication channels for relation aggregation and entity aggregation during the evolution of the historical sequence. Experiments conducted on five public datasets show that RETIA has made great improvements across several evaluation metrics. Our released code is available at https://***/CGCL-codes/RETIA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature 39

Breaking Barriers in Physical-World Adversarial Examples: Im...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Yichen Chou, Yuxuan Zhou, Ziqi Zhang, Hangtao Wan, Wei Hu, Shengshan Li, Minghui National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China

ISBN: (纸本)157735897X

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model's incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method's superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method's effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Revealing the significant role of band structure asymmetry on thermoelectric bipolar conduction

引用

Physical Review B 2025年第4期111卷 045203-045203页

作者： Jiamin Qiu Shizhen Zhi Peng Zhao Jian Wang Xiaojing Ma Sheng Ye Chenhao Lin Xuanhe Zhang Zuoxu Wu School of Materials Science and Engineering and Institute of Materials Genome and Big Data Harbin Institute of Technology Shenzhen 518055 People's Republic of China School of Science and Ministry of Industry and Information Technology Key Lab of Micro-Nano Optoelectronic Information System Harbin Institute of Technology Shenzhen 518055 China

Bipolar conduction, which is widely observed in various materials, plays a deleterious role in the thermoelectric properties. Traditionally, the single-band model is often applied to understand the transport properties of thermoelectric materials. However, it ignores the contribution from minority carriers and is incapable of quantifying the bipolar conduction. Herein, a general and feasible approach for calculating all the temperature-dependent transport properties based on the two-band model has been developed. In addition to the reduced electron Fermi energy and reduced band-gap energy, band structure asymmetry has been identified to play a significant role in bipolar conduction. Importantly, the effect of band structure asymmetry on bipolar conduction has been highlighted by using the Mg3Bi2−xSbx alloy as a typical example. Our results demonstrate that the band structure asymmetry is of great significance to the materials' thermoelectric performance.

关键词： Energy gap

来源：评论

学校读者我要写书评

暂无评论

Reveal training performance mystery between Tensor Flow and PyTorch in the single GPU environment

引用

science China(Information sciences) 2022年第1期65卷 147-163页

作者： Hulin DAI Xuan PENG Xuanhua SHI Ligang HE Qian XIONG Hai JIN National Engineering Research Center for Big Data Technology and System Service Computing Technology and System LabSchool of Computer Science and Technology Huazhong University of Science and Technology Department of Computer Science University of Warwick

Deep learning has gained tremendous success in various fields while training deep neural networks(DNNs) is very compute-intensive, which results in numerous deep learning frameworks that aim to offer better usability and higher performance to deep learning practitioners. Tensor Flow and Py Torch are the two most popular frameworks. Tensor Flow is more promising within the industry context, while Py Torch is more appealing in academia. However, these two frameworks differ much owing to the opposite design philosophy:static vs dynamic computation graph. Tensor Flow is regarded as being more performance-friendly as it has more opportunities to perform optimizations with the full view of the computation graph. However, there are also claims that Py Torch is faster than Tensor Flow sometimes, which confuses the end-users on the choice between them. In this paper, we carry out the analytical and experimental analysis to unravel the mystery of comparison in training speed on single-GPU between Tensor Flow and Py Torch. To ensure that our investigation is as comprehensive as possible, we carefully select seven popular neural networks, which cover computer vision, speech recognition, and natural language processing(NLP). The contributions of this work are two-fold. First, we conduct the detailed benchmarking experiments on Tensor Flow and Py Torch and analyze the reasons for their performance difference. This work provides the guidance for the end-users to choose between these two frameworks. Second, we identify some key factors that affect the performance,which can direct the end-users to write their models more efficiently.

关键词： deep learning performance comparison TensorFlow PyTorch

来源：评论

学校读者我要写书评

暂无评论

EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding 39

EvoChart: A Benchmark and a Self-Training Approach Towards R...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Huang, Muye Lai, Han Zhang, Xinyu Wu, Wenjun Ma, Jie Zhang, Lingling Liu, Jun School of Computer Science and Technology Xi’an Jiaotong University China MOE KLINNS Lab Xi’an Jiaotong University China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering China

ISBN: (纸本)157735897X

Chart understanding enables automated data analysis for humans, which requires models to achieve highly accurate visual comprehension. While existing Visual Language Models (VLMs) have shown progress in chart understanding, the lack of high-quality training data and comprehensive evaluation benchmarks hinders VLM chart comprehension. In this paper, we introduce EvoChart, a novel self-training method for generating synthetic chart data to enhance VLMs’ capabilities in real-world chart comprehension. We also propose EvoChart-QA, a noval benchmark for measuring models’ chart comprehension abilities in real-world scenarios. Specifically, EvoChart is a unique self-training data synthesis approach that simultaneously produces high-quality training corpus and a high-performance chart understanding model. EvoChart-QA consists of 650 distinct real-world charts collected from 140 different websites and 1,250 expert-curated questions that focus on chart understanding. Experimental results on various open-source and proprietary VLMs tested on EvoChart-QA demonstrate that even the best proprietary model, GPT-4o, achieves only 49.8% accuracy. Moreover, the EvoChart method significantly boosts the performance of open-source VLMs on real-world chart understanding tasks, achieving 54.2% accuracy on EvoChart-QA. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

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：