检索结果-内蒙古大学图书馆

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

作者： Yunzhe Hu Difan Zou Dong Xu School of Computing and Data Science The University of Hong Kong School of Computing and Data Science & Institute of Data Science The University of Hong Kong

ISBN: (纸本)9798331314385

Deep neural networks have long been criticized for being black-box. To unveil the inner workings of modern neural architectures, a recent work [45] proposed an information-theoretic objective function called Sparse Rate Reduction (SRR) and interpreted its unrolled optimization as a Transformer-like model called Coding Rate Reduction Transformer (CRATE). However, the focus of the study was primarily on the basic implementation, and whether this objective is optimized in practice and its causal relationship to generalization remain elusive. Going beyond this study, we derive different implementations by analyzing layer-wise behaviors of CRATE, both theoretically and empirically. To reveal the predictive power of SRR on generalization, we collect a set of model variants induced by varied implementations and hyperparameters and evaluate SRR as a complexity measure based on its correlation with generalization. Surprisingly, we find out that SRR has a positive correlation coefficient and outperforms other baseline measures, such as path-norm and sharpness-based ones. Furthermore, we show that generalization can be improved using SRR as regularization on benchmark image classification datasets. We hope this paper can shed light on leveraging SRR to design principled models and study their generalization ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed Truss Computation in Dynamic Graphs

引用

Tsinghua science and Technology 2023年第5期28卷 873-887页

作者： Ziwei Mo Qi Luo Dongxiao Yu Hao Sheng Jiguo Yu Xiuzhen Cheng School of Computer Science and Technology Shandong UniversityQingdao 266200China State Key Laboratory of Software Development Environment School of Computer Science and Engineering and the Beijing Advanced Innovation Center for Big Data and Brain ComputingBeihang UniversityBeijing 100191China Big Data Institute Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353China

Large-scale graphs usually exhibit global sparsity with local cohesiveness,and mining the representative cohesive subgraphs is a fundamental problem in graph *** k-truss is one of the most commonly studied cohesive subgraphs,in which each edge is formed in at least k 2 triangles.A critical issue in mining a k-truss lies in the computation of the trussness of each edge,which is the maximum value of k that an edge can be in a *** works mostly focus on truss computation in static graphs by sequential ***,the graphs are constantly changing dynamically in the real *** study distributed truss computation in dynamic graphs in this *** particular,we compute the trussness of edges based on the local nature of the k-truss in a synchronized node-centric distributed *** decomposing the trussness of edges by relying only on local topological information is possible with the proposed distributed decomposition ***,the distributed maintenance algorithm only needs to update a small amount of dynamic information to complete the *** experiments have been conducted to show the scalability and efficiency of the proposed algorithm.

关键词： distributed algorithm dynamic graph graph mining cohesive subgraph k-truss

来源：评论

学校读者我要写书评

暂无评论

Movie Reviews using Sentiment Analysis with Natural Language API 8

Movie Reviews using Sentiment Analysis with Natural Language...

引用

8th IEEE International Conference on science, Technology, Engineering and Mathematics, ICONSTEM 2023

作者： Athish, V.P. Rajeswari, D. Sree Nandha, S. Srm Institute of Science and Technology School of Computing Dept. of Data Science and Business Systems Tamilnadu Kattankulathur India

ISBN: (纸本)9798350347791

Sentiment Analysis is the process of analyzing sentiment of a piece of text by identifying polarity or writer's attitude towards any topic or product such as positive, neutral or negative. This paper uses sentiment analysis on movie reviews in twitter data, which is the most dominant public social media and its data is accessible using their own Twitter API. Words and misspellings make sentiment analysis for twitter data, harder due to the existence of slang words and bad spelling. This work uses Hadoop for the various features it provides over the API. The proposed work uses the knowledge base approach using lexica analyzer for sentiment analysis of movie reviews. The assigned score for movies is 100. The proposed work get all the positive, negative and neutral comments to judge "how good"or "how bad"the movie is. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A recurrent neural network architecture for android mobile data analysis for detecting malware infected data

引用

Soft computing 2024年第21期28卷 12917-12928页

作者： Murugan, Prabhu Manimaran, A. Sundar, Ramesh Dakshinamoorthy, Prabakar Rajaram, Gnanajeyaraman Garg, Shruti Department of ECE Saveetha School of Engineering Simats Chennai602105 India Department of Artificial Intelligence and Machine Learning Saveetha School of Engineering Simats Chennai602105 India Department of Netwoking and Communication School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India Department of Data Science and Business System School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India Department of Applied Machine Learning Saveetha School of Engineering Saveetha Institute of Medical and Technological Sciences Tamilnadu Chennai India Birla Institute of Technology Mesra Ranchi India

One of the latest modern communication devices is a mobile device seriously affected by multiple malware. Malware is a virus software installed automatically by hackers on various computing devices. Malware corrupts the system software, kills *.exe files, and tries to access user-sensitive data from the device. Around the world, 80% of people use smartphones, and 70% use Android phones. All Android phones are installed with anti-virus software but not used properly. Thus, it creates a pathway for malware to enter Android mobile devices and deploy vulnerabilities. Several earlier methods have focused on using the malware detection method by analyzing static data, which cannot identify the dynamic behavior of the malware. Thus, this paper implemented one of the deep learning algorithms, RNN, for identifying and detecting malware activities in Android mobile devices statically and dynamically. An IoT network architecture is proposed for experimenting with the RNN algorithms verifying the performance. The results of the RNN method show that it is better than other models in malware detection in mobile devices. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Large Language Model-Based Event Relation Extraction with Rationales 31

Large Language Model-Based Event Relation Extraction with Ra...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Hu, Zhilei Li, Zixuan Jin, Xiaolong Bai, Long Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of SciencesSchool of Computer Science and Technology University of Chinese Academy of Sciences

ISBN: (纸本)9798891761964

Event Relation Extraction (ERE) aims to extract various types of relations between different events within texts. Although Large Language Models (LLMs) have demonstrated impressive capabilities in many natural language processing tasks, existing ERE methods based on LLMs still face three key challenges: (1) Time Inefficiency: The existing pairwise method of combining events and determining their relations is time-consuming for LLMs. (2) Low Coverage: When dealing with numerous events in a document, the limited generation length of fine-tuned LLMs restricts the coverage of their extraction results. (3) Lack of Rationale: Essential rationales concerning the results that could enhance the reasoning ability of the model are overlooked. To address these challenges, we propose LLMERE, an LLM-based approach with rationales for the ERE task. LLMERE transforms ERE into a question-and-answer task that may have multiple answers. By extracting all events related to a specified event at once, LLMERE reduces time complexity from O(n2) to O(n), compared to the pairwise method. Subsequently, LLMERE enhances the coverage of extraction results by employing a partitioning strategy that highlights only a portion of the events in the document at a time. In addition to the extracted results, LLMERE is also required to generate corresponding rationales/reasons behind them, in terms of event coreference information or transitive chains of event relations. Experimental results on three widely used datasets show that LLMERE achieves significant improvements over baseline methods. © 2025 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

Inductive Link Prediction in N-ary Knowledge Graphs 31

Inductive Link Prediction in N-ary Knowledge Graphs

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Wei, Jiyao Guan, Saiping Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi School of Computer Science and Technology University of Chinese Academy of Sciences Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9798891761964

N-ary Knowledge Graphs (NKGs), where a fact can involve more than two entities, have gained increasing attention. Link Prediction in NKGs (LPN) aims to predict missing elements in facts to facilitate the completion of NKGs. Current LPN methods implicitly operate under a closed-world assumption, meaning that the sets of entities and roles are fixed. These methods focus on predicting missing elements within facts composed of entities and roles seen during training. However, in reality, new facts involving unseen entities and roles frequently emerge, requiring completing these facts. Thus, this paper proposes a new task, Inductive Link Prediction in NKGs (ILPN), which aims to predict missing elements in facts involving unseen entities and roles in emerging NKGs. To address this task, we propose a Meta-learning-based Nary knowledge Inductive Reasoner (MetaNIR), which employs a graph neural network with meta-learning mechanisms to embed unseen entities and roles adaptively. The obtained embeddings are used to predict missing elements in facts involving unseen elements. Since no existing dataset supports this task, three datasets are constructed to evaluate the effectiveness of MetaNIR. Extensive experimental results demonstrate that MetaNIR consistently outperforms representative models across all datasets. © 2025 Association for Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

SpeedLoader: An I/O efficient scheme for heterogeneous and distributed LLM operation 38

SpeedLoader: An I/O efficient scheme for heterogeneous and d...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhang, Yiqi You, Yang Institute of Data Science National University of Singapore Singapore119077 Singapore School of Computing National University of Singapore Singapore119077 Singapore

With the surging growth of model parameters, foundation models pose unprecedented challenges to traditional computational infrastructures. These large models inherently require substantial accelerator memory to accommodate massive tensors during pre-training, fine-tuning, and even inference stages, making it even more challenging to deploy a model with restricted computational resources. Given this challenge, distribution and offloading the model states are two major solutions. Partitioning the required states to participating workers, and storing them in lower speed media, such as host DRAM and block devices, largely alleviate the accelerator memory pressure. However, the prohibitive costs of tensor communication render it a theoretically plausible yet practically inefficient solution. Previous efforts to improve efficiency include maximizing rematerialization and employing chunk-based tensor management to reduce host-device communication. Despite these efforts, the reported training throughput only achieves 36.54% of model FLOPs utilization (MFUs), still not comparable to full on-device training. In this work, we redesign the data flow of heterogeneous hardware and sharded model training to minimize the excessive communication overhead. Our proposed scheme significantly enhances training and inference throughput of large language models under restrictive computational resources. We confirmed a large leap in effective compute time by looking into the kernel-level runtime behavior of our trials, where the MFUs can achieve up to 51%. Compared to the state-of-the-art approach, our framework robustly achieves remarkable speedups from 3x to 30x in multiple distributed heterogeneous training setups and inference speedups of 1.5x to 2.35x without compromising arithmetic precision. © 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 Macro- and Micro-Hierarchical Transfer Learning Framework for Cross-Domain Fake News Detection 25

A Macro- and Micro-Hierarchical Transfer Learning Framework ...

引用

34th ACM Web Conference, WWW 2025

作者： Yang, Xuankai Wang, Yan Zhang, Xiuzhen Wang, Shoujin Wang, Huaxiong Lam, Kwok Yan School of Computing Macquarie University Sydney Australia School of Computing Technologies RMIT University Melbourne Australia Data Science Institute University of Technology Sydney Sydney Australia School of Physical and Mathematical Sciences Nanyang Technological University Singapore Singapore College of Computing and Data Science Nanyang Technological University Singapore Singapore

ISBN: (纸本)9798400712746

Cross-domain fake news detection aims to mitigate domain shift and improve detection performance by transferring knowledge across domains. Existing approaches transfer knowledge based on news content and user engagements from a source domain to a target domain. However, these approaches face two main limitations, hindering effective knowledge transfer and optimal fake news detection performance. Firstly, from a micro perspective, they neglect the negative impact of veracity-irrelevant features in news content when transferring domain-shared features across domains. Secondly, from a macro perspective, existing approaches ignore the relationship between user engagement and news content, which reveals shared behaviors of common users across domains and can facilitate more effective knowledge transfer. To address these limitations, we propose a novel macro- and micro- hierarchical transfer learning framework (MMHT) for cross-domain fake news detection. Firstly, we propose a micro-hierarchical disentangling module to disentangle veracity-relevant and veracity-irrelevant features from news content in the source domain for improving fake news detection performance in the target domain. Secondly, we propose a macro-hierarchical transfer learning module to generate engagement features based on common users’ shared behaviors in different domains for improving effectiveness of knowledge transfer. Extensive experiments on real-world datasets demonstrate that our framework significantly outperforms the state-of-the-art baselines. © 2025 Copyright held by the owner/author(s).

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Monochromatic Image Dehazing Using Enhanced Feature Extraction Techniques in Deep Learning

Monochromatic Image Dehazing Using Enhanced Feature Extracti...

引用

2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering, ICECONF 2023

作者： Doshi, Nisarg Bhavsar, Sagar Rajeswari, D. Srinivasan, R. School of Computing College of Engineering and Technology SRM Institute of Science and Technology Department of Data Science and Business Systems Kattankulathur603203 India School of Computing College of Engineering and Technology SRM Institute of Science and Technology Department of Computing Technologies Kattankulathur603203 India

ISBN: (纸本)9798350334357

Images photographed in foggy weather usually have poor visibility. To mitigate this problem researchers have come up with various image dehazing techniques. Now, more than ever, high-quality images that can be used to glean maximum information from autonomous systems are in high demand. This research work uses different Deep Learning (DL) architectures to draw out essential details from the picture and localize the information recovered to reduce the haze from the picture. The paper investigates to remove the hazes from the dehazed images using DL techniques. The first task of this proposed work attempts three pre-processing techniques namely, air light estimation, contextual regularization and boundary constraint. The second task of this work is to identify the suitable DL model to extract clear images from dehazed images. Evaluation metrics are PSNR value and SSIM value are used to estimate the values of dehazed images compared with clear images. Experimental results proves that AOD-Net outperforms good result with respect to PSNR value. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Intelligent Chatbot for Hospital Recommendation System 2

Intelligent Chatbot for Hospital Recommendation System

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Rajkumar, K. Ragupathi, T. Karthikeyan, S. School of Computing Srm Institute of Science and Technology Department of Data Science and Business Systems Tamil Nadu Kattankulathur India Department of Computer Science and Engineering Bangalore562112 India

ISBN: (纸本)9798350371055

The main objective of this project is to create a user-friendly intelligent chatbot for Medical guidance and support. This application has been classified into two different modes based on user preference, those are Online and Offline modes of interaction. In the Online mode of interaction, there is no need for any automation, there will be a real person at the other end answering user queries. Users can even ask for untrained data and will receive instant replies. This application is similar to a normal chat application, but the main disadvantage is that a real person is needed at the other end at all times. In the Offline mode of conversation which is entirely automated the user will be performing an interaction with the chatbot itself. The chatbot must consist of data sets and trained data collection, in this process there is no need for any real person, the chatbot itself will reply instantly based on the trained data. The chatbot will be more accurate when a large number of data is trained. This application is compatible with working in various browsers and varied networks. The Admin of the application plays a significant role. Admin can access all the given functions and is responsible for data training. data training plays a vital role in this application, the trained data will be used by the chatbot while answering user queries i.e. Offline mode. This chatbot application can be accessed by several users at the same time, where IP address plays the main role. The main function of this application is that user can post their corresponding queries and the application will be providing relevant information based on queries. The Latest Modern chatbots are used in applications where simple interaction is needed, for example, service and marketing technology to provide answers such as products, services, and consultancy. If the customer's queries don't match with the trained data sets, the customer will be escalated to manual interaction i.e. Online mode. © 2024 IE

关键词： Automated Intelligent Chat IP Address Offline mode Online mode Trained data

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：