检索结果-内蒙古大学图书馆

Node transfer with graph contrastive learning for class-imbalanced node classification

学校读者我要写书评

暂无评论

Neural Networks 2025年 190卷

作者： Yangding Li Xiangchao Zhao Yangyang Zeng Hao Feng Jiawei Chai Hao Xie Shaobin Fu Shichao Zhang College of Information Science and Engineering Hunan Normal University Changsha China Hunan Provincial Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin China

In graph representation learning, the class imbalance problem is a significant challenge that has received much attention from academics. Although current approaches have shown promising results, they have not adequately addressed the problems of node quantity imbalance and feature space imbalance in datasets. This research presents a node transfer with graph contrastive learning framework (NT-GCL) that aims to improve the representation capabilities of graph neural networks for minority classes nodes by balancing node quantity and feature space distributions. First, the proposed node transfer algorithm redistributes misclassified nodes from majority classes to achieve a balanced distribution of node quantity and feature space. This approach effectively prevents the feature space of minority classes from being compressed by majority classes during information propagation, further mitigating potential imbalance issues. Subsequently, the self-supervised contrastive learning strategy is employed to train the model without relying on labels, reducing the bias introduced by labeled data. Experiments conducted with various encoders on six public datasets demonstrate that NT-GCL exhibits strong competitiveness in class-imbalanced node classification.

关键词：

Large Generative Model Assisted 3D Semantic Communication

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Feibo Peng, Yubo Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua You, Xiaohu Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China School of Information Science and Engineering Hunan Normal University Changsha China Changsha Social Laboratory of Artificial Intelligence Hunan University of Technology and Business Changsha China The Department of Computer Science Brunel University London United Kingdom The School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom Changchun Institute of Technology China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The Frontiers Science Center for Mobile Information Communication and Security National Mobile Communications Research Laboratory Southeast University Nanjing China The Purple Mountain Laboratories Nanjing China

Semantic Communication (SC) is a novel paradigm for data transmission in 6G. However, there are several challenges posed when performing SC in 3D scenarios: 1) 3D semantic extraction;2) Latent semantic redundancy;and 3) Uncertain channel estimation. To address these issues, we propose a Generative AI Model assisted 3D SC (GAM-3DSC) system. Firstly, we introduce a 3D Semantic Extractor (3DSE), which employs generative AI models, including Segment Anything Model (SAM) and Neural Radiance Field (NeRF), to extract key semantics from a 3D scenario based on user requirements. The extracted 3D semantics are represented as multi-perspective images of the goal-oriented 3D object. Then, we present an Adaptive Semantic Compression Model (ASCM) for encoding these multi-perspective images, in which we use a semantic encoder with two output heads to perform semantic encoding and mask redundant semantics in the latent semantic space, respectively. Next, we design a conditional Generative adversarial network and Diffusion model aided-Channel Estimation (GDCE) to estimate and refine the Channel State information (CSI) of physical channels. Finally, simulation results demonstrate the advantages of the proposed GAM-3DSC system in effectively transmitting the goal-oriented 3D scenario. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

Overview of the Tenth Dialog System Technology Challenge: DSTC10

学校读者我要写书评

暂无评论

IEEE/ACM Transactions on Audio Speech and language processing 2024年 32卷 765-778页

作者： Yoshino, Koichiro Chen, Yun-Nung Crook, Paul Kottur, Satwik Li, Jinchao Hedayatnia, Behnam Moon, Seungwhan Fei, Zhengcong Li, Zekang Zhang, Jinchao Feng, Yang Zhou, Jie Kim, Seokhwan Liu, Yang Jin, Di Papangelis, Alexandros Gopalakrishnan, Karthik Hakkani-Tur, Dilek Damavandi, Babak Geramifard, Alborz Hori, Chiori Shah, Ankit Zhang, Chen Li, Haizhou Sedoc, Joao D'haro, Luis F. Banchs, Rafael Rudnicky, Alexander Guardian Robot Project R-IH RIKEN 2-2-2 Hikaridai Seika Shoraku619-0288 Japan Information Science Nara Institute of Science and Technology Ikoma630-0101 Japan Computer Science and Information Engineering National Taiwan University Taipei10617 Taiwan Inc. Palo AltoCA95054 United States Alexa AI *** Inc. SunnyvaleCA94089 United States Meta Seattle RedmondWA98052 United States Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Tencent AI Lab Beijing Beijing China Kexueyuan South Road Zhongguancun Beijing100190 China Beijing 100190 China Alexa AI *** Inc. SunnyvaleCA United States 1120 Enterprise way Sunnyvale94089 United States *** Inc. SeattleWA United States Menlo Park CA United States Audio and Speech Group Mitsubishi Electric Research Laboratories CambridgeMA02139-1955 United States Carnegie Mellon University Department of Language and Information Technologies or just Carnegie Mellon University Pittsburgh United States National University of Singapore Singapore Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Shenzhen Research Institute of Big Data School of Data Science Chinese University of Hong Kong Shenzhen518172 China New York University New YorkNY United States ETSI de Telecomunicacion - Speech Technology and Machine Learning Group Universidad Politecnica de Madrid Ciudad Universitaria Madrid28040 Spain Nanyang Technological University Singapore Singapore Carnegie Mellon University PittsburghPA United States

This article introduces the Tenth Dialog System Technology Challenge (DSTC-10). This edition of the DSTC focuses on applying end-to-end dialog technologies for five distinct tasks in dialog systems, namely 1. Incorporation of Meme images into open domain dialogs, 2. Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations, 3. Situated Interactive Multimodal dialogs, 4. Reasoning for Audio Visual Scene-Aware Dialog, and 5. Automatic Evaluation and Moderation of Open-domainDialogue Systems. This article describes the task definition, provided datasets, baselines, and evaluation setup for each track. We also summarize the results of the submitted systems to highlight the general trends of the state-of-the-art technologies for the tasks. © 2023 The Authors.

关键词： Job analysis

Large AI Model-Based Semantic Communications

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jiang, Feibo Peng, Yubo Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua You, Xiaohu Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China School of Information Science and Engineering Hunan Normal University Changsha China Changsha Social Laboratory of Artificial Intelligence Hunan University of Technology and Business Changsha China Department of Computer Science Brunel University London United Kingdom School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom Changchun Institute of Technology China National Mobile Communications Research Laboratory Southeast University Nanjing210096 China

Semantic communication (SC) is an emerging intelligent paradigm, offering solutions for various future applications like metaverse, mixed reality, and the Internet of Everything. However, in current SC systems, the construction of the knowledge base (KB) faces several issues, including limited knowledge representation, frequent knowledge updates, and insecure knowledge sharing. Fortunately, the development of the large AI model (LAM) provides new solutions to overcome the above issues. Here, we propose a LAM-based SC framework (LAM-SC) specifically designed for image data, where we first apply the segment anything model (SAM)-based KB (SKB) that can split the original image into different semantic segments by universal semantic knowledge. Then, we present an attention-based semantic integration (ASI) to weigh the semantic segments generated by SKB without human participation and integrate them as the semanticaware image. Additionally, we propose an adaptive semantic compression (ASC) encoding to remove redundant information in semantic features, thereby reducing communication overhead. Finally, through simulations, we demonstrate the effectiveness of the LAM-SC framework and the possibility of applying the LAM-based KB in future SC paradigms. Copyright © 2023, The Authors. All rights reserved.

关键词： Latent semantic analysis

Knowledge Base Enhanced Topic Modeling

学校读者我要写书评

暂无评论

Knowledge Base Enhanced Topic Modeling

IEEE International Conference on Big Knowledge (ICBK)

作者： Dandan Song Jingwen Gao Jinhui Pang Lejian Liao Lifei Qin Lab of High Volume language Information Processing & Cloud Computing Applications School of Computer Science & Technology Beijing Institute of Technology Jianpu Technology Inc

ISBN: (数字)9781728181561

ISBN: (纸本)9781728181578

Topic models, such as Latent Dirichlet Allocation (LDA), are successful in learning hidden topics and has been widely applied in text mining. There are many recently developed augmented topic modeling methods to utilize metadata information. However, the effect of topic models is still not comparable to humans. We think one key point is that humans have background knowledge, which is essential for topic understanding. Inspired by this, we propose a knowledge base enhanced topic model in this paper. We take knowledge bases as good presentations of human knowledge, with huge collections of entities and their relations. We assume that documents with related entities tend to have similar topic distributions. Based on this assumption, we compute document similarity information via the linked entities and then use it as a constraint for LDA. More specifically, we embed entities in a low-dimensional space via DeepWalk and use Entity Movers Distance to efficiently and effectively measure the similarities between documents. The results of experiments over two real-world datasets show that our method boosts the LDA model on the document classification while no supervision information is needed.

关键词： Knowledge based systems Task analysis Computational modeling Semantics Optimization Resource management Transforms

Robust Deep Learning Framework for Predicting Respiratory Anomalies and Diseases 42

学校读者我要写书评

暂无评论

Robust Deep Learning Framework for Predicting Respiratory An...

42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, EMBC 2020

作者： Pham, Lam McLoughlin, Ian Phan, Huy Tran, Minh Nguyen, Truc Palaniappan, Ramaswamy University of Kent School of Computing Medway Kent United Kingdom University of Science and Technology of China National Engineering Laboratory for Speech and Language Information Processing Hefei China Queen Mary University School of Electronic Engineering and Computer Science London United Kingdom University of Oxford Nuffield Department of Anaesthesia United Kingdom Graz University of Technology Signal Processing and Speech Communication Lab Austria

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119908

This paper presents a robust deep learning framework developed to detect respiratory diseases from recordings of respiratory sounds. The complete detection process firstly involves front end feature extraction where recordings are transformed into spectrograms that convey both spectral and temporal information. Then a back-end deep learning model classifies the features into classes of respiratory disease or anomaly. Experiments, conducted over the ICBHI benchmark dataset of respiratory sounds, evaluate the ability of the framework to classify sounds. Two main contributions are made in this paper. Firstly, we provide an extensive analysis of how factors such as respiratory cycle length, time resolution, and network architecture, affect final prediction accuracy. Secondly, a novel deep learning based framework is proposed for detection of respiratory diseases and shown to perform extremely well compared to state of the art methods. © 2020 IEEE.

关键词： Network architecture

Characterizing Multi-domain False News and Underlying User Effects on Chinese Weibo

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sheng, Qiang Cao, Juan Bernard, H. Russell Shu, Kai Li, Jintao Liu, Huan Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Institute for Social Science Research Arizona State University TempeAZ United States Department of Computer Science Illinois Institute of Technology ChicagoIL United States Computer Science and Engineering Arizona State University TempeAZ United States

False news that spreads on social media has proliferated over the past years and has led to multi-aspect threats in the real world. While there are studies of false news on specific domains (like politics or health care), little work is found comparing false news across domains. In this article, we investigate false news across nine domains on Weibo, the largest Twitter-like social media platform in China, from 2009 to 2019. The newly collected data comprise 44,728 posts in the nine domains, published by 40,215 users, and reposted over 3.4 million times. Based on the distributions and spreads of the multi-domain dataset, we observe that false news in domains that are close to daily life like health and medicine generated more posts but diffused less effectively than those in other domains like politics, and that political false news had the most effective capacity for diffusion. The widely diffused false news posts on Weibo were associated strongly with certain types of users - by gender, age, etc. Further, these posts provoked strong emotions in the reposts and diffused further with the active engagement of false-news starters. Our findings have the potential to help design false news detection systems in suspicious news discovery, veracity prediction, and display and explanation. The comparison of the findings on Weibo with those of existing work demonstrates nuanced patterns, suggesting the need for more research on data from diverse platforms, countries, or languages to tackle the global issue of false news. The code and new anonymized dataset are available at https://***/ICTMCG/Characterizing-Weibo-Multi-Domain-False-News. © 2022, CC BY-NC-ND.

关键词： social networking (online)

Robust acoustic scene classification using a multi-spectrogram encoder-decoder framework

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Pham, Lam Phan, Huy Nguyen, Truc Palaniappan, Ramaswamy Mertins, Alfred McLoughlin, Ian University of Kent School of Computing Medway Kent United Kingdom Signal Processing and Speech Communication Lab Graz University of Technology Austria Institute for Signal Processing University of Lubeck Germany National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of China Hefei China

This article proposes an encoder-decoder network model for Acoustic Scene Classification (ASC), the task of identifying the scene of an audio recording from its acoustic signature. We make use of multiple low-level spectrogram features at the front-end, transformed into higher level features through a well-trained CNN-DNN front-end encoder. The high level features and their combination (via a trained feature combiner) are then fed into different decoder models comprising random forest regression, DNNs and a mixture of experts, for back-end classification. We report extensive experiments to evaluate the accuracy of this framework for various ASC datasets, including LITIS Rouen and IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE) 2016 Task 1, 2017 Task 1, 2018 Tasks 1A & 1B and 2019 Tasks 1A & 1B. The experimental results highlight two main contributions;the first is an effective method for high-level feature extraction from multi-spectrogram input via the novel C-DNN architecture encoder network, and the second is the proposed decoder which enables the framework to achieve competitive results on various datasets. The fact that a single framework is highly competitive for several different challenges is an indicator of its robustness for performing general ASC tasks. Copyright © 2020, The Authors. All rights reserved.

关键词： Classification (of information)

Robust deep learning framework for predicting respiratory anomalies and diseases

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Pham, Lam McLoughlin, Ian Phan, Huy Tran, Minh Nguyen, Truc Palaniappan, Ramaswamy University of Kent School of Computing Medway Kent United Kingdom National Engineering Laboratory for Speech and Language Information Processing University of Science and Technology of China Hefei China Nuffield Department of Anaesthesia University of Oxford United Kingdom Signal Processing and Speech Communication Lab Graz University of Technology Austria

关键词： Recurrent neural networks