IEEE Transactions on Knowledge and Data Engineering最新文献_第10页

Automated Data Cleaning can Hurt Fairness in Machine Learning-Based Decision Making 自动数据清理会损害基于机器学习决策的公平性

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2024-02-13 DOI: 10.1109/TKDE.2024.3365524

Shubha Guha;Falaah Arif Khan;Julia Stoyanovich;Sebastian Schelter

{"title":"Automated Data Cleaning can Hurt Fairness in Machine Learning-Based Decision Making","authors":"Shubha Guha;Falaah Arif Khan;Julia Stoyanovich;Sebastian Schelter","doi":"10.1109/TKDE.2024.3365524","DOIUrl":"https://doi.org/10.1109/TKDE.2024.3365524","url":null,"abstract":"In this paper, we interrogate whether data quality issues track demographic group membership (based on sex, race and age) and whether automated data cleaning — of the kind commonly used in production ML systems — impacts the fairness of predictions made by these systems. To the best of our knowledge, the impact of data cleaning on fairness in downstream tasks has not been investigated in the literature. We first analyse the tuples flagged by common error detection strategies in five research datasets. We find that, while specific data quality issues, such as higher rates of missing values, are associated with membership in historically disadvantaged groups, poor data quality does not generally track demographic group membership. As a follow-up, we conduct a large-scale empirical study on the impact of automated data cleaning on fairness, involving more than 26,000 model evaluations. We observe that, while automated data cleaning is unlikely to worsen accuracy, it is more likely to worsen fairness than to improve it, especially when the cleaning techniques are not carefully chosen. Furthermore, we find that the positive or negative impact of a particular cleaning technique often depends on the choice of fairness metric and group definition (single-attribute or intersectional). We make our code and experimental results publicly available. The analysis we conducted in this paper is difficult, primarily because it requires that we think holistically about disparities in data quality, disparities in the effectiveness of data cleaning methods, and impacts of such disparities on ML model performance for different demographic groups. Such holistic analysis can and should be supported by data engineering tools, and requires substantial data engineering research. Towards this goal, we discuss open research questions, envision the development of fairness-aware data cleaning methods, and their integration into complex pipelines for ML-based decision making.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"7368-7379"},"PeriodicalIF":8.9,"publicationDate":"2024-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Amalur: The Convergence of Data Integration and Machine Learning 阿玛卢尔：数据整合与机器学习

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2024-01-23 DOI: 10.1109/TKDE.2024.3357389

Ziyu Li;Wenbo Sun;Danning Zhan;Yan Kang;Lydia Chen;Alessandro Bozzon;Rihan Hai

{"title":"Amalur: The Convergence of Data Integration and Machine Learning","authors":"Ziyu Li;Wenbo Sun;Danning Zhan;Yan Kang;Lydia Chen;Alessandro Bozzon;Rihan Hai","doi":"10.1109/TKDE.2024.3357389","DOIUrl":"10.1109/TKDE.2024.3357389","url":null,"abstract":"Machine learning (ML) training data is often scattered across disparate collections of datasets, called \u0000<italic>data silos\u0000. This fragmentation poses a major challenge for data-intensive ML applications: integrating and transforming data residing in different sources demand a lot of manual work and computational resources. With data privacy constraints, data often cannot leave the premises of data silos; hence model training should proceed in a decentralized manner. In this work, we present a vision of bridging traditional data integration (DI) techniques with the requirements of modern machine learning systems. We explore the possibilities of utilizing metadata obtained from data integration processes for improving the effectiveness, efficiency, and privacy of ML models. Towards this direction, we analyze ML training and inference over data silos. Bringing data integration and machine learning together, we highlight new research opportunities from the aspects of systems, representations, factorized learning, and federated learning.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"7353-7367"},"PeriodicalIF":8.9,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10412203","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139949054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

引用次数: 0

Managing Metaverse Data Tsunami: Actionable Insights 管理元数据海啸：可行的见解

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2024-01-16 DOI: 10.1109/TKDE.2024.3354960

Bingxue Zhang;Gang Chen;Beng Chin Ooi;Mike Zheng Shou;Kian-Lee Tan;Anthony K. H. Tung;Xiaokui Xiao;James Wei Luen Yip;Meihui Zhang

引用次数: 0

A Framework for Elastic Adaptation of User Multiple Intents in Sequential Recommendation 顺序推荐中用户多重意图弹性适应框架

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2024-01-16 DOI: 10.1109/TKDE.2024.3354796

Zhikai Wang;Yanyan Shen

{"title":"A Framework for Elastic Adaptation of User Multiple Intents in Sequential Recommendation","authors":"Zhikai Wang;Yanyan Shen","doi":"10.1109/TKDE.2024.3354796","DOIUrl":"10.1109/TKDE.2024.3354796","url":null,"abstract":"Recently, substantial research has been conducted on sequential recommendation, with the objective of forecasting the subsequent item by leveraging a user's historical sequence of interacted items. Prior studies employ both capsule networks and self-attention techniques to effectively capture diverse underlying intents within a user's interaction sequence, thereby achieving the most advanced performance in sequential recommendation. However, users could potentially form novel intents from fresh interactions as the lengths of user interaction sequences grow. Consequently, models need to be continually updated or even extended to adeptly encompass these emerging user intents, referred as incremental multi-intent sequential recommendation. In this paper, we propose an effective \u0000<bold>I\u0000ncremental learning framework for user \u0000<bold>M\u0000ulti-intent \u0000<bold>A\u0000daptation in sequential recommendation called IMA, which augments the traditional fine-tuning strategy with the existing-intents retainer, new-intents detector, and projection-based intents trimmer to adaptively expand the model to accommodate user's new intents and prevent it from forgetting user's existing intents. Furthermore, we upgrade the IMA into an \u0000<bold>E\u0000lastic \u0000<bold>M\u0000ulti-intent \u0000<bold>A\u0000daptation (EMA) framework which can elastically remove inactive intents and compress user intent vectors under memory space limit. Extensive experiments on real-world datasets verify the effectiveness of the proposed IMA and EMA on incremental multi-intent sequential recommendation, compared with various baselines.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"7340-7352"},"PeriodicalIF":8.9,"publicationDate":"2024-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139949032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Pre-Training General Trajectory Embeddings With Maximum Multi-View Entropy Coding 用最大多视图熵编码预训练一般轨迹嵌入

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2023-12-27 DOI: 10.1109/TKDE.2023.3347513

Yan Lin;Huaiyu Wan;Shengnan Guo;Jilin Hu;Christian S. Jensen;Youfang Lin

{"title":"Pre-Training General Trajectory Embeddings With Maximum Multi-View Entropy Coding","authors":"Yan Lin;Huaiyu Wan;Shengnan Guo;Jilin Hu;Christian S. Jensen;Youfang Lin","doi":"10.1109/TKDE.2023.3347513","DOIUrl":"https://doi.org/10.1109/TKDE.2023.3347513","url":null,"abstract":"Spatio-temporal trajectories provide valuable information about movement and travel behavior, enabling various downstream tasks that in turn power real-world applications. Learning trajectory embeddings can improve task performance but may incur high computational costs and face limited training data availability. Pre-training learns generic embeddings by means of specially constructed pretext tasks that enable learning from unlabeled data. Existing pre-training methods face (i) difficulties in learning general embeddings due to biases towards certain downstream tasks incurred by the pretext tasks, (ii) limitations in capturing both travel semantics and spatio-temporal correlations, and (iii) the complexity of long, irregularly sampled trajectories. To tackle these challenges, we propose Maximum Multi-view Trajectory Entropy Coding (MMTEC) for learning general and comprehensive trajectory embeddings. We introduce a pretext task that reduces biases in pre-trained trajectory embeddings, yielding embeddings that are useful for a wide variety of downstream tasks. We also propose an attention-based discrete encoder and a NeuralCDE-based continuous encoder that extract and represent travel behavior and continuous spatio-temporal correlations from trajectories in embeddings, respectively. Extensive experiments on two real-world datasets and three downstream tasks offer insight into the design properties of our proposal and indicate that it is capable of outperforming existing trajectory embedding methods.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"9037-9050"},"PeriodicalIF":8.9,"publicationDate":"2023-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Kairos: Enabling Prompt Monitoring of Information Diffusion Over Temporal Networks 启航：实现对时态网络信息扩散的及时监测

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2023-12-27 DOI: 10.1109/TKDE.2023.3347621

Haifa Gaza;Jaewook Byun

{"title":"Kairos: Enabling Prompt Monitoring of Information Diffusion Over Temporal Networks","authors":"Haifa Gaza;Jaewook Byun","doi":"10.1109/TKDE.2023.3347621","DOIUrl":"https://doi.org/10.1109/TKDE.2023.3347621","url":null,"abstract":"Analyses of temporal graphs provide valuable insights into temporal data through the use of two analytical approaches: temporal evolution and temporal information diffusion. The former shows how a network evolves over time; the latter explains how information spreads throughout a network over time. Systems have been mainly proposed to efficiently handle graph snapshots, which are suitable for temporal evolution but inappropriate for temporal information diffusion. For analyses of temporal information diffusion, temporal graph traversal platforms have recently been proposed; however, it is still infeasible to handle infinitely evolving temporal data, especially for monitoring applications. In this paper, we propose an incremental approach and its graph processing engine, Kairos, to enable prompt monitoring of temporal information diffusion. This approach makes it possible to immediately process diffusion results for sources of interest by traversing a part of the whole network, which avoids full traversals influenced by a small change in the network, thus making monitoring applications feasible. The recipes for implementing incremental versions of existing temporal graph traversal algorithms and metrics will make it easier for users to build their ad-hoc programs.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"8607-8621"},"PeriodicalIF":8.9,"publicationDate":"2023-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10374549","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645551","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

引用次数: 0

Change Point Detection in Multi-Channel Time Series via a Time-Invariant Representation 通过时不变表示法检测多通道时间序列中的变化点

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2023-12-26 DOI: 10.1109/TKDE.2023.3347356

Zhenxiang Cao;Nick Seeuws;Maarten De Vos;Alexander Bertrand

引用次数: 0

When Learned Indexes Meet Persistent Memory: The Analysis and the Optimization 当学习索引遇到持久内存：分析与优化

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2023-12-25 DOI: 10.1109/TKDE.2023.3342825

Lixiao Cui;Yijing Luo;Yusen Li;Gang Wang;Xiaoguang Liu

{"title":"When Learned Indexes Meet Persistent Memory: The Analysis and the Optimization","authors":"Lixiao Cui;Yijing Luo;Yusen Li;Gang Wang;Xiaoguang Liu","doi":"10.1109/TKDE.2023.3342825","DOIUrl":"https://doi.org/10.1109/TKDE.2023.3342825","url":null,"abstract":"The emerging persistent memory (PM) is increasingly being leveraged to construct high-performance and persistent indexes. By exploiting data distribution, recent learned indexes open up a new index design paradigm. Some prior studies try to refit the learned index according to the features of PM. However, they neglect to analyze the performance of existing learned index schemes on PM. In this paper, we provide a comprehensive analysis of learned indexes on PM and propose two optimization methods to improve the performance. In particular, we evaluate ALEX, PGM-index, and XIndex after converting them to persistent indexes. With appropriate modifications, some design choices of volatile learned index still show favorable performance on PM under workloads with simple data distribution. But they perform poorly when the data distribution becomes complex. According to the experiment results, we summarize some instructive insights and optimize persistent learned indexes for complex data distributions with two methods: 1) a cost-based insertion pattern selection to minimize PM writes and 2) recoverable internal nodes selective persistence to decrease the overhead of internal lookups. Our evaluations demonstrate the performance of optimized ALEX is 2.09x/1.53x of the original ALEX in insert/search. Meanwhile, it also outperforms the specific-designed persistent learned index.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"9517-9531"},"PeriodicalIF":8.9,"publicationDate":"2023-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Classification With Trust: A Supervised Approach Based on Sequential Ellipsoidal Partitioning 信任分类：基于序列椭圆分区的监督方法

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2023-12-25 DOI: 10.1109/TKDE.2023.3345658

Ranjani Niranjan;Sachit Rao

{"title":"Classification With Trust: A Supervised Approach Based on Sequential Ellipsoidal Partitioning","authors":"Ranjani Niranjan;Sachit Rao","doi":"10.1109/TKDE.2023.3345658","DOIUrl":"https://doi.org/10.1109/TKDE.2023.3345658","url":null,"abstract":"Standard metrics of performance of classifiers, such as accuracy and sensitivity, do not reveal the trust or confidence in the predicted labels of data. While other metrics such as the computed probability of a label or the signed distance from a hyperplane can act as a trust measure, these are subjected to heuristic thresholds. This paper presents a convex optimization-based supervised classifier that sequentially partitions a dataset into several ellipsoids, where each ellipsoid contains nearly all points of the same label. By stating classification rules based on this partitioning, Bayes’ formula is then applied to calculate a trust score to a label assigned to a test datapoint determined from these rules. The proposed Sequential Ellipsoidal Partitioning Classifier (SEP-C) exposes dataset irregularities, such as degree of overlap, without requiring a separate exploratory data analysis. The rules of classification, which are free of hyperparameters, are also not affected by class-imbalance, the underlying data distribution, or number of features. SEP-C does not require the use of non-linear kernels when the dataset is not linearly separable. The performance, and comparison with other methods, of SEP-C is demonstrated on the XOR-problem, circle dataset, and other open-source datasets.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"7757-7771"},"PeriodicalIF":8.9,"publicationDate":"2023-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142636508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Acquiring New Knowledge Without Losing Old Ones for Effective Continual Dialogue Policy Learning 掌握新知识，不丢旧知识，有效开展持续对话政策学习

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2023-12-20 DOI: 10.1109/TKDE.2023.3344727

Huimin Wang;Yunyan Zhang;Yifan Yang;Yefeng Zheng;Kam-Fai Wong

{"title":"Acquiring New Knowledge Without Losing Old Ones for Effective Continual Dialogue Policy Learning","authors":"Huimin Wang;Yunyan Zhang;Yifan Yang;Yefeng Zheng;Kam-Fai Wong","doi":"10.1109/TKDE.2023.3344727","DOIUrl":"https://doi.org/10.1109/TKDE.2023.3344727","url":null,"abstract":"Dialogue policy learning is the core decision-making module of a task-oriented dialogue system. Its primary objective is to assist users to achieve their goals effectively in as few turns as possible. A practical dialogue-policy agent must be able to expand its knowledge to handle new scenarios efficiently without affecting its performance. Nevertheless, when adapting to new tasks, existing dialogue-policy agents often fail to retain their existing (old) knowledge. To overcome this predicament, we propose a novel continual dialogue-policy model which tackles the issues of “not forgetting the old” and “acquiring the new” from three different aspects: (1) For effective old-task preservation, we introduce the forgetting preventor which uses a behavior cloning technique to force the agent to take actions consistent with the replayed experience to retain the policy trained on historic tasks. (2) For new-task acquisition, we introduce the adaption accelerator which employs an invariant risk minimization mechanism to produce a stable policy predictor to avoid spurious corrections in training data. (3) For reducing the storage cost of the replayed experience, we introduce a replay manager which helps regularly clean up the old data. The effectiveness of the proposed model is evaluated both theoretically and experimentally and demonstrated favorable results.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"7569-7584"},"PeriodicalIF":8.9,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10366832","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142645553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

引用次数: 0