Improving the performance of data systems for join operations has long been a critical challenge. Recently, substantial attention has been focused on optimizing multi-way join performance, particularly in reducing the overhead caused by generating intermediate tuples that do not contribute to the final result. In this paper, we propose a novel algorithm called SieveJoin, which extends the established Bloomjoin approach to support multi-way joins. SieveJoin sets a new benchmark for the efficiency of join query execution. A key innovation of SieveJoin is its ability to propagate Bloom filters along the join path, allowing the system to terminate early and avoid producing superfluous intermediate results. The primary design objective of SieveJoin is to efficiently estimate join results using Bloom filters, while maintaining minimal memory overhead. We analyze the bottlenecks associated with deferred multi-way joins and detail how Bloom filters are utilized to suppress the creation of redundant intermediate tuples. To assess the effectiveness of SieveJoin, we conduct a comprehensive experimental evaluation using the TPC-H benchmark, citation datasets, and a synthetic dataset. Our results compare SieveJoin with a state-of-the-art column-store database and a worst-case optimal join algorithm, highlighting its advantages in both response time and memory usage.

Zero-shot Anomaly Detection (ZSAD) is an emerging task in industrial settings. It aims to detect anomalies in a target dataset without training samples, which is crucial for sample scarcity and data privacy. Existing methods largely rely on CLIP, leveraging its internal knowledge to detect anomalies. However, due to its pre-training on natural image-text pairs, CLIP suffers from domain shift, favoring global semantics over fine-grained defect detection in industrial images. Furthermore, most existing methods employ fixed text prompt to guide the model, which is difficult to describe diverse and unseen anomalies, leading to poor accuracy. To address these limitations, we propose a Detail-guided Dual-modal Enhancement Model (DDE-CLIP) for the ZSAD task. Firstly, we designed the Detail Feature Reinforcement Module (DFRM) to capture local representations of minute defects. Its specialized design effectively enhances the model's perception of fine-grained anomalies and enables the pre-trained CLIP model to better adapt to the unique visual characteristics of industrial images. Subsequently, we introduced the Visual-guided Text Refinement Module (VTRM), which can dynamically optimize text prompts based on the input image's visual content (particularly the detail features captured by DFRM). This ensures the accurate reflection of text prompts on specific semantics of various defects, thereby significantly enhancing the alignment between vision and text for unseen anomalies. Overall, our DDE-CLIP uses detail features to enhance both image and text modalities, effectively addressing the challenges of ZSAD. Extensive experiments on 7 real-world industrial product datasets demonstrate that DDE-CLIP exhibits superior detection and localization capabilities compared to other methods. The code is available at https://github.com/zhushengxinyue/DDE-CLIP.

Cardinality estimation has long been crucial for cost-based database optimizers in identifying optimal query execution plans, attracting significant attention over the past decades. While recent advancements have significantly improved the accuracy of multi-table join query estimations, these methods introduce challenges such as higher space overhead, increased latency, and greater complexity, especially when integrated with the binary join framework. In this paper, we introduce a novel cardinality estimation method named TKHist, which addresses these challenges by relaxing the uniformity assumption in histograms. TKHist captures bin-wise non-uniformity information, enabling accurate cardinality estimation for join queries without filter predicates. Furthermore, we explore the attribute independent assumption, which can lead to significant over-estimation rather than under-estimation in multi-table join queries. To address this issue, we propose the dominating join path correlation discovery algorithm to highlight and manage correlations between join keys and filter predicates. Our extensive experiments on popular benchmarks demonstrate that TKHist reduces error variance by 2-3 orders of magnitude compared to SOTA methods, while maintaining comparable or lower memory usage.

Data isolation poses a significant challenge to efficient big data query processing, as data providers are often reluctant to share their raw data due to security concerns. Current federated query systems address this issue by employing Secure Multi-Party Computation (SMC) and Differential Privacy (DP) to facilitate secure and collaborative computation. However, these privacy-preserving methods rely on cryptographic protocols, which introduce substantial computational overhead, slowing query processing by up to 1,000 times compared to plaintext queries. While sampling methods have been explored to enhance federated query systems, they frequently fail to strike a balance between accuracy and speed. To address the limitations above, we propose a secure federated approximate query system based on a deep classifier (SAQDC). This system utilizes deep learning techniques to accelerate query processing while integrating SMC and Differential Privacy to achieve an optimal balance between privacy and efficiency by allowing each data provider to train classifiers using Multi-Layer Perceptron (MLP) and Deep Set architectures, which predict query relative errors across different modules.Based on the prediction errors generated by the classifier, queries are assigned to the most appropriate approximate query model and the differential privacy parameters are adjusted to enhance query accuracy. This approach enhances query speed, preserves accuracy, and effectively mitigates malicious differential privacy attacks. We demonstrate SAQDC's superior performance through extensive experiments on three large-scale datasets.

Trajectory similarity computation is a fundamental functionality in trajectory data mining, with wide-ranging applications in location-based services. Position embedding, which transforms GPS points into embedding vectors, plays a critical role in learning-based trajectory similarity models. The quality of these embeddings significantly impacts the performance of the models on downstream tasks. Existing methods fail to satisfy all good properties, i.e., global, continuous, unique, and dynamic, thereby limiting the development of trajectory similarity computation in both local and global scenarios. Inspired by linear counting systems, such as the decimal system, we first propose the łambda-base circular system to embed positions on the circle, then introduce the multi-base global embedding method GPE to encode global positions into vectors. Experiments conducted on five real-world datasets with nine baseline methods demonstrate that the GPE achieves state-of-the-art performance across four key evaluations in downstream tasks.

With the widespread use of GPS devices and the advancement of location-based services, a vast amount of trajectory data has been collected and mined for various applications. Trajectory clustering, which categorizes trajectories into distinct groups, is the fundamental functionality of trajectory data mining. The challenge is how to cluster on a mass of trajectory data efficiently and universally with satisfying results. The raw trajectory clustering algorithms are universal, but trapped in the dilemma between efficiency and desirable results. Other approaches, such as density-based, road network-based, and deep learning-based algorithms, encounter issues like high time complexity, loss of trajectory integrity, reliance on road networks, and data quality during training. To tackle these challenges, we first propose the efficient KMCT (k-Means Clustering of Trajectories) algorithm based on a semantic interpolation transformation to cluster raw trajectories and achieve satisfying results. Additionally, we introduce the DA-KMCT (Density Accelerated k-Means Clustering of Trajectories) algorithm to further boost the clustering process based on trajectory densities and an optimized centroid selecting strategy. Moreover, we present a novel clustering evaluation method called IOD, which efficiently estimates clustering results on large-scale datasets with linear time complexity. Experimental results on real-world datasets demonstrate that KMCT and DA-KMCT outperform five related methods in terms of clustering quality and time efficiency, and the proposed IOD evaluation shows a strong correlation with the Silhouette Coefficient, offering a reliable and efficient alternative for evaluating clustering results.

The automatic generation of radiological imaging reports aims to produce accurate and coherent clinical descriptions based on X-ray images. This facilitates clinicians in completing the arduous task of report writing and advances clinical automation. The primary challenge in radiological imaging report generation lies in accurately capturing and describing abnormal regions in the images under data bias conditions, resulting in the generation of lengthy texts containing image details. Existing methods mostly rely on prior knowledge such as medical knowledge graphs, corpora, and image databases to assist models in generating more precise textual descriptions. However, these methods still struggle to identify rare anomalies in the images. To address this issue, we propose a two-stage training model, named CLR2G, based on cross-modal contrastive learning. This model delegates the task of capturing anomalies, particularly those challenging for the generative model trained with cross-entropy loss under data bias conditions, to a specialized abnormality capture component. Specifically, we employ a semantic matching loss function to train additional abnormal image and text encoders through cross-modal contrastive learning, facilitating the capture of 13 common anomalies. We utilize the anomalous image features, text features and their confidence probabilities as a posteriori knowledge to help the model generate accurate image reports. Experimental results demonstrate the state-of-the-art performance of our method on two widely used public datasets, IU-Xray and MIMIC-CXR.

Inductive Link Prediction (ILP) aims to predict links for unseen entities in emerging Knowledge Graphs (KGs), where a more realistic scenario is that unseen entities do not emerge all at once but emerge sequentially in multiple stages. Unfortunately, existing studies neglect the sequential-emerging nature of KGs and simplify this scenario into multi-batch unseen entities emerging simultaneously. Subsequently, two problems arise and restrict the performance of existing methods: (1) lack of the capability to model the long-dependency interactions between entities across different stages; (2) unable to exploit the incremental characteristics when KGs emerge in sequence. To address the problems effectively, we dive into the practical scenario formulated as Sequential-emerging Knowledge Graphs (SEKGs), and propose a novel model entitled ISE2(Inductive Sequential Emerging Embedding). Specifically, ISE2is composed of the following two modules: (1) a relational graph-transformer network is designed to capture long-dependency interactions with the full-graph receptive field; (2) an adaptive attention mechanism is developed to iteratively integrate emerging KGs into a whole, fully utilizing the incremental characteristic in SEKGs. Furthermore, a new benchmark that conforms to the data distribution of real-world sequential-emerging is constructed. The experimental results demonstrate the superiority of ISE2compared with the state-of-the-art methods in SEKGs scenario.

Modern databases face formidable challenges when called to join (several) massive tables. Joins (especially when entailing many-to-many joins) are very time- and resource-consuming, join results can be too big to keep in memory, and performing analytics/learning tasks over them costs dearly in terms of time, resources, and money (in the cloud). Moreover, although random sampling is a promising idea to mitigate the above problems, the current state of the art leaves lots of room for improvements. With this paper we contribute a principled solution, coined PGMJoins. PGMJoins adapts Probabilistic Graphical Models to deriving provably random samples of the join result for (n-way) key joins, many-to-many joins, and cyclic and acyclic joins. PGMJoins contributes optimizations both for deriving the structure of the graph and for PGM inference. It also contributes a novel Sum-Product Message Passing Algorithm (SP-MPA) to make a uniform sample of the joint distribution (join result) efficiently and a novel way to deal with cyclic joins. Despite the use of PGMs, the learned joint distribution is not approximated, and the uniform samples are drawn from the true distribution. Our experimentation using queries and datasets from TPC-H, JOB, TPC-DS, and Twitter shows PGMJoins to outperform the state of the art (by 2X-28X).

In the era of big data, computing exact answers to analytical queries becomes prohibitively expensive. This greatly increases the value of approaches that can compute efficiently approximate, but highly-accurate, answers to analytical queries. Alas, the state of the art still suffers from many shortcomings: Errors are still high unless large memory investments are made. Many important analytics tasks are not supported. Query response times are too long and thus approaches rely on parallel execution of queries atop large big data analytics clusters, in-situ or in the cloud, whose acquisition/use costs dearly. Hence, the following questions are crucial: Can we develop AQP engines that reduce response times by orders of magnitude, ensure high accuracy, and support most aggregate functions? With smaller memory footprints and small overheads to build the state upon which they are based? With this paper, we show that the answers to all questions above can be positive. The paper presents DBEst, a system based on Machine Learning models (regression models and probability density estimators). It will discuss its limitations, promises, and how it can complement existing systems. It will substantiate its advantages using queries and data from the TPC-DS benchmark and real-life datasets, compared against state of the art AQP engines.