Abstract: Data uncertainty is a major issue in database systems due to application inaccuracies. Probabilistic databases can store uncertain data and provide confident answers through querying. When systems propagate uncertainty, query or mining results may…
Abstract: KNN is a popular data mining algorithm. It has been successfully used for data analysis in many computer science research areas. This paper shows that KNN classification, despite its success, faces many challenges, including…
Abstract: A two-stage learning scheme must capture consensus cluster structures for graph-based multi-view clustering. Learn similarity graph matrices of multiple views, then combine them into a superior graph matrix. Most current methods learn pairwise similarities…
Abstract: Many reviews-rating integration studies have improved recommendation performance. These works still have flaws: (1) Dynamically integrating review and interaction data features is often overlooked, but treating them equally may lead to a misunderstanding of…
Abstract: User identification across multiple datasets has many applications, and recent research has increased on this topic. Most existing works identify users with a single input data type, such as (I) identifying a user across…
Abstract: Data matter. How can we quantitatively and objectively evaluate data? Pricing data, or information goods, has been studied and practiced in many disciplines, including economics, marketing, electronic commerce, data management, data mining, and machine…
Abstract: Finding the densest lasting subgraphs in large dynamic graphs, which takes into account subgraph pattern duration, is an important but understudied problem. Expectation-Maximization with Utility functions (EMU) is a stochastic framework that extends the…
Abstract: Semantic networks connect concepts with semantic relations. It has binary and multiplex semantic networks. The associated fact prediction link prediction task mines the high-level network representation to infer implicitly connected facts. Previous associated fact…
Abstract: Data anomaly detection has many real-world applications. Outlier detection algorithms are abundant, but most have hidden assumptions and restrictions. This paper proposes a novel, yet effective outlier learning algorithm that decomposes the full attributes…
Abstract: Representative selection involves selecting few informative exemplars from large datasets. Data selection methods rarely handle non-linear data structures, sample concise and non-redundant subsets, reject outliers, and produce interpretable results. This paper introduces MOSAIC, a…
Abstract: Finance, medicine, and education generate time series at an unprecedented rate. Exploring heterogeneous, variable-length, and misaligned time series requires many dynamic time warping distances. The computational costs of elastic distances cause unacceptable response times….
Abstract: Cloud computing platforms risk data leakage, so security and privacy are major concerns. Data can leak while in storage, processing, or moving within a cloud or between cloud infrastructures, such as private to public…
WhatsApp us