IEEE Transactions on Big Data最新文献

{"title":"Deep Cross-Modal Hashing With Ranking Learning for Noisy Labels","authors":"Zhenqiu Shu;Yibing Bai;Kailing Yong;Zhengtao Yu","doi":"10.1109/TBDATA.2024.3423704","DOIUrl":"https://doi.org/10.1109/TBDATA.2024.3423704","url":null,"abstract":"Deep hashing technology has recently become an essential tool for cross-modal retrieval on large-scale datasets. However, their performances heavily depend on accurate annotations to train the hashing model. In real applications, we usually only obtain low-quality label annotations owing to labor and time consumption limitations. To mitigate the performance degradation caused by noisy labels, in this paper, we propose a robust deep hashing method, called deep hashing with ranking learning (DHRL), for cross-modal retrieval. The proposed DHRL method consists of a refined semantic concept alignment module and a ranking-swapping module. In this first module, we adopt two transformers to perform the semantic alignment tasks between different modalities on a set of refined concepts, and then convert them into hash codes to reduce heterogeneous differences between multimodalities. The second module first identifies the noisy labels in the training set and ranks them according to ranking loss. Then it swaps the ranking information of different modal network branches. Unlike existing robust hashing methods for assuming noise distribution, our proposed DHRL method requires no prior assumptions for the input data. Extensive experiments on three benchmark datasets have shown that our proposed DHRL method has stronger advantages over other state-of-the-art hashing methods.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 2","pages":"553-565"},"PeriodicalIF":7.5,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive Superpixel Segmentation With Non-Uniform Seed Initialization","authors":"Xinlin Xie;Jing Fan;Xinying Xu;Gang Xie","doi":"10.1109/TBDATA.2024.3423719","DOIUrl":"https://doi.org/10.1109/TBDATA.2024.3423719","url":null,"abstract":"Superpixel segmentation is a powerful image pre-processing tool in computer vision applications. However, fewer superpixel segmentation methods consider automatically determining the number of initial superpixels. Focusing on high-precision and connectivity, we propose a superpixel segmentation algorithm with non-uniform seed initialization. The proposed algorithm can adaptively determine the number and the position of initial seeds, and is robust to the segmentation of small objects and slender regions. First, we propose a seed initialization scheme based on the side of the circumscribed rectangle of the small object and interval boundary gradient. To enhance the regularity of superpixels, we equally added seeds for grids with sparse seed distribution. Second, we construct a weighted distance measure with search region and feature constraints, which reduces the computational complexity and enhances the precision of pixel label assignment. Finally, we quantify the disconnected regions are present in abundance, and propose a post-processing method based on the area of predefined small objects. The proposed method can significantly improve the connectivity and regularity of the generated superpixels. Extensive experiments on the widely-used BSDS and CamVid datasets demonstrate that the non-uniform seed initialization is effective, and the performance of the proposed superpixel segmentation is favorably compared with the state-of-the-art methods.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 2","pages":"620-634"},"PeriodicalIF":7.5,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10587110","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Survey on Truth Discovery: Concepts, Methods, Applications, and Opportunities","authors":"Shuang Wang;He Zhang;Quan Z. Sheng;Xiaoping Li;Zhu Sun;Taotao Cai;Wei Emma Zhang;Jian Yang;Qing Gao","doi":"10.1109/TBDATA.2024.3423677","DOIUrl":"https://doi.org/10.1109/TBDATA.2024.3423677","url":null,"abstract":"In the era of data information explosion, there are different observations on an object (e.g., the height of the Himalayas) from different sources on the web, social sensing, crowd sensing, and data sensing applications. Observations from different sources on an object can conflict with each other due to errors, missing records, typos, outdated data, etc. How to discover truth facts for objects from various sources is essential and urgent. In this paper, we aim to deliver a comprehensive and exhaustive survey on truth discovery problems from the perspectives of concepts, methods, applications, and opportunities. We first systematically review and compare problems from objects, sources, and observations. Based on these problem properties, different methods are analyzed and compared in depth from observation with single or multiple values, independent or dependent sources, static or dynamic sources, and supervised or unsupervised learning, followed by the surveyed applications in various scenarios. For future studies in truth discovery fields, we summarize the code sources and datasets used in above methods. Finally, we point out the potential challenges and opportunities on truth discovery, with the goal of shedding light and promoting further investigation in this area.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 2","pages":"314-332"},"PeriodicalIF":7.5,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SGAMF: Sparse Gated Attention-Based Multimodal Fusion Method for Fake News Detection","authors":"Pengfei Du;Yali Gao;Linghui Li;Xiaoyong Li","doi":"10.1109/TBDATA.2024.3414341","DOIUrl":"https://doi.org/10.1109/TBDATA.2024.3414341","url":null,"abstract":"In the field of fake news detection, deep learning techniques have emerged as superior performers in recent years. Nevertheless, the majority of these studies primarily concentrate on either unimodal feature-based methodologies or image-text multimodal fusion techniques, with a minimal focus on the fusion of unstructured text features and structured tabular features. In this study, we present SGAMF, a Sparse Gated Attention-based Multimodal Fusion strategy, designed to amalgamate text features and auxiliary features for the purpose of fake news identification. Compared with traditional multimodal fusion methods, SGAMF can effectively balance accuracy and inference time while selecting the most important features. A novel sparse-gated-attention mechanism has been proposed which instigates a shift in text representation conditioned on auxiliary features, thereby selectively filtering out non-essential features. We have further put forward an enhanced ALBERT for the encoding of text features, capable of balancing efficiency and accuracy. To corroborate our methodology, we have developed a multimodal COVID-19 fake news detection dataset. Comprehensive experimental outcomes on this dataset substantiate that our proposed SGAMF delivers competitive performance in comparison to the existing state-of-the-art techniques in terms of accuracy and <inline-formula><tex-math>$F_{1}$</tex-math></inline-formula> score.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 2","pages":"540-552"},"PeriodicalIF":7.5,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross-Modality and Equity-Aware Graph Pooling Fusion: A Bike Mobility Prediction Study","authors":"Xi Yang;Suining He;Kang G. Shin;Mahan Tabatabaie;Jing Dai","doi":"10.1109/TBDATA.2024.3414280","DOIUrl":"https://doi.org/10.1109/TBDATA.2024.3414280","url":null,"abstract":"We propose an equity-aware <underline><i>GRA</i></u>ph-fusion differentiable <underline><i>P</i></u>ooling neural network to accurately predict the spatio-temporal urban mobility (e.g., station-level bike usage in terms of departures and arrivals) with <underline><i>E</i></u>quity (<monospace>GRAPE</monospace>). <monospace>GRAPE</monospace> consists of two independent hierarchical graph neural networks for two mobility systems—one as a target graph (i.e., a bike sharing system) and the other as an auxiliary graph (e.g., a taxi system). We have designed a convolutional fusion mechanism to jointly fuse the target and auxiliary graph embeddings and extract the shared spatial and temporal mobility patterns within the embeddings to enhance prediction accuracy. To further improve the equity of bike sharing systems for diverse communities, we focus on the bike resource allocation and model prediction performance, and propose to regularize the predicted bike resource as well as the accuracy across advantaged and disadvantaged communities, and thus mitigate the potential unfairness in the predicted bike sharing usage. Our evaluation of over 23 million bike rides and 100 million taxi trips in New York City and Chicago has demonstrated <monospace>GRAPE</monospace> to outperform all of the baseline approaches in terms of prediction accuracy (by 15.80% for NYC and 50.55% for Chicago on average) and social equity awareness (by 32.44% and 24.43% in terms of resource fairness for NYC and Chicago, and 13.36% and 16.52% in terms of performance fairness).","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 1","pages":"286-302"},"PeriodicalIF":7.5,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficiently Transfer User Profile Across Networks","authors":"Mengting Diao;Zhongbao Zhang;Sen Su;Shuai Gao;Huafeng Cao;Junda Ye","doi":"10.1109/TBDATA.2024.3414321","DOIUrl":"https://doi.org/10.1109/TBDATA.2024.3414321","url":null,"abstract":"User profiling has very important applications for many downstream tasks. Most existing methods only focus on modeling user profiles of one social network with plenty of data. However, user profiles are difficult to acquire, especially when the data is scarce. Fortunately, we observed that similar users have similar behavior patterns in different social networks. Motivated by such observations, in this paper, we for the first time propose to study the user profiling problem from the transfer learning perspective. We design two efficient frameworks for User Profile transferring acrOss Networks, i.e., UPON and E-UPON. In UPON, we first design a novel graph convolutional networks based characteristic-aware domain attention model to find user dependencies within and between domains (i.e., social networks). We then design a dual-domain weighted adversarial learning method to address the domain shift problem existing in the transferring procedure. In E-UPON, we optimize UPON in terms of computational complexity and memory. Specifically, we design a mini-cluster gradient descent based graph representation algorithm to shrink the searching space and ensure parallel computation. Then we use an adaptive cluster matching method to adjust the clusters of users. Experimental results on Twitter-Foursquare dataset demonstrate that UPON and E-UPON outperform the state-of-the-art models.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 1","pages":"271-285"},"PeriodicalIF":7.5,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation","authors":"Heng Xu;Tianqing Zhu;Lefeng Zhang;Wanlei Zhou;Philip S. Yu","doi":"10.1109/TBDATA.2024.3409947","DOIUrl":"https://doi.org/10.1109/TBDATA.2024.3409947","url":null,"abstract":"Federated learning is a promising privacy-preserving paradigm for distributed machine learning. In this context, there is sometimes a need for a specialized process called machine unlearning, which is required when the effect of some specific training samples needs to be removed from a learning model due to privacy, security, usability, and/or legislative factors. However, problems arise when current centralized unlearning methods are applied to existing federated learning, in which the server aims to remove all information about a class from the global model. Centralized unlearning usually focuses on simple models or is premised on the ability to access all training data at a central node. However, training data cannot be accessed on the server under the federated learning paradigm, conflicting with the requirements of the centralized unlearning process. Additionally, there are high computation and communication costs associated with accessing clients’ data, especially in scenarios involving numerous clients or complex global models. To address these concerns, we propose a more effective and efficient federated unlearning scheme based on the concept of model explanation. Model explanation involves understanding deep networks and individual channel importance, so that this understanding can be used to determine which model channels are critical for classes that need to be unlearned. We select the most influential channels within an already-trained model for the data that need to be unlearned and fine-tune only influential channels to remove the contribution made by those data. In this way, we can simultaneously avoid huge consumption costs and ensure that the unlearned model maintains good performance. Experiments with different training models on various datasets demonstrate the effectiveness of the proposed approach.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 2","pages":"524-539"},"PeriodicalIF":7.5,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Reinforcement Learning Framework for N-Ary Document-Level Relation Extraction","authors":"Chenhan Yuan;Ryan Rossi;Andrew Katz;Hoda Eldardiry","doi":"10.1109/TBDATA.2024.3410099","DOIUrl":"https://doi.org/10.1109/TBDATA.2024.3410099","url":null,"abstract":"Knowledge Bases (KBs) have become more complex because some facts in KBs include more than two entities. The construction and completion of these KBs require a new relation extraction task to retrieve complex facts from the text. To address this issue, we present a new N-ary Document-Level relation extraction task that involves extracting relations that 1) include an arbitrary number of entities, and 2) can span multiple sentences within a document. This new task requires inferring relation labels and entity completeness, i.e., whether the entities in the document are (insufficient to describe the relation. We propose a reinforcement learning-based relation classifier training framework that can adapt most existing binary document-level relation extractors to this task. Extensive experimental evaluation demonstrates that our proposed framework is effective in reducing the impact of noise introduced by distant supervision or unrelated sentences in the document.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 2","pages":"512-523"},"PeriodicalIF":7.5,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143611811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic Recognition of Cyberbullying in the Web of Things and social media using Deep Learning Framework","authors":"Fahd N. Al-Wesabi;Marwa Obayya;Jamal Alsamri;Rana Alabdan;Nojood O Aljehane;Sana Alazwari;Fahad F. Alruwaili;Manar Ahmed Hamza;A Swathi","doi":"10.1109/TBDATA.2024.3409939","DOIUrl":"https://doi.org/10.1109/TBDATA.2024.3409939","url":null,"abstract":"The Web of Things (WoT) is a network that facilitates the formation and distribution of information its users make. Young people nowadays, digital natives, have no trouble relating to others or joining groups online since they have grown up in a world where new technology has pushed communications to a nearly real-time level. Shared private messages, rumours, and sexual comments are all examples of online harassment that have led to several recent cases worldwide. Therefore, academics have been more interested in finding ways to recognise bullying conduct on these platforms. The effects of cyberbullying, a terrible form of online misbehaviour, are distressing. It takes several documents, but the text is predominant on social networks. Intelligent systems are required for the automatic detection of such occurrences. Most previous research has used standard machine-learning techniques to tackle this issue. The increasing pervasiveness of cyberbullying in WoT and other social media platforms is a significant cause for worry that calls for robust responses to prevent further harm. This study offers a unique method of leveraging the deep learning (DL) model binary coyote optimization-based Convolutional Neural Network (BCNN) in social networks to identify and classify cyberbullying. An essential part of this method is the combination of DL-based abuse detection and feature subset selection. To efficiently detect and address cases of cyberbullying via social media, the proposed system incorporates many crucial steps, including preprocessing, feature selection, and classification. A binary coyote optimization (BCO)-based feature subset selection method is presented to enhance classification efficiency. To improve the accuracy of cyberbullying categorization, the BCO algorithm efficiently chooses a selection of key characteristics. Cyberbullying must be tracked and classified across all internet channels, and Convolutional Neural Network (CNN) is constructed. With a best-case accuracy of 99.5% on Formspring, 99.7% on Twitter, and 99.3% on Wikipedia, the suggested algorithm successfully identified the vast majority of cyberbullying content.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 1","pages":"259-270"},"PeriodicalIF":7.5,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Blockchain-Enabled Secure Collaborative Model Learning Using Differential Privacy for IoT-Based Big Data Analytics","authors":"Prakash Tekchandani;Abhishek Bisht;Ashok Kumar Das;Neeraj Kumar;Marimuthu Karuppiah;Pandi Vijayakumar;Youngho Park","doi":"10.1109/TBDATA.2024.3394700","DOIUrl":"https://doi.org/10.1109/TBDATA.2024.3394700","url":null,"abstract":"With the rise of Big data generated by Internet of Things (IoT) smart devices, there is an increasing need to leverage its potential while protecting privacy and maintaining confidentiality. Privacy and confidentiality in Big Data aims to enable data analysis and machine learning on large-scale datasets without compromising the dataset sensitive information. Usually current Big Data analytics models either efficiently achieves privacy or confidentiality. In this article, we aim to design a novel blockchain-enabled secured collaborative machine learning approach that provides privacy and confidentially on large scale datasets generated by IoT devices. Blockchain is used as secured platform to store and access data as well as to provide immutability and traceability. We also propose an efficient approach to obtain robust machine learning model through use of cryptographic techniques and differential privacy in which the data among involved parties is shared in a secured way while maintaining privacy and confidentiality of the data. The experimental evaluation along with security and performance analysis show that the proposed approach provides accuracy and scalability without compromising the privacy and security.","PeriodicalId":13106,"journal":{"name":"IEEE Transactions on Big Data","volume":"11 1","pages":"141-156"},"PeriodicalIF":7.5,"publicationDate":"2024-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}