Data Preparation (DP), which involves tasks such as data cleaning, imputation and integration, is a fundamental process in data-driven applications. Recently, Large Language Models (LLMs) fine-tuned for DP tasks, i.e., DP-LLMs, have achieved state-of-the-art performance. However, transferring DP-LLMs to novel datasets and tasks typically requires a substantial amount of labeled data, which is impractical in many real-world scenarios. To address this, we propose a knowledge augmentation framework for data preparation, dubbed KNOWTRANS. This framework allows DP-LLMs to be transferred to novel datasets and tasks with a few data points, significantly decreasing the dependence on extensive labeled data. KNOWTRANS comprises two components: Selective Knowledge Concentration and Automatic Knowledge Bridging. The first component re-uses knowledge from previously learned tasks, while the second automatically integrates additional knowledge from external sources. Extensive experiments on 13 datasets demonstrate the effectiveness of KNOWTRANS. KNOWTRANS boosts the performance of the state-of-the-art DP-LLM, Jellyfish-7B, by an average of 4.93%, enabling it to outperform both GPT-4 and GPT-4o.

Nearest neighbor search (NNS) is fundamental for high-dimensional space retrieval and impacts various fields, such as pattern recognition, information retrieval, recommendation systems, and vector database management. Among existing NNS methods, graph-based methods often excel in query accuracy and efficiency. However, these methods face significant challenges, including high construction costs and difficulties with dynamic data updates. Recent efforts have focused on combining graph methods with hashing, quantization, and tree-based approaches to address these issues, but problems with large index sizes and update performance remain unresolved. In response, this paper proposes GTI, a novel, lightweight, and dynamic graph-based tree index for high-dimensional NNS. GTI constructs a tree index built across the entire dataset and employs a lightweight graph index at the level 1 of the tree to significantly reduce graph construction costs. It also features effective data insertion and deletion algorithms that enable logarithmic real-time updates. Additionally, we have developed an effective NNS algorithm for GTI, which not only achieves approximate search performance on par with SOTA graph-based methods but also supports exact NNS. Extensive experiments on six real-world datasets demonstrate that GTI achieves an approximately 10× improvement in update efficiency compared to SOTA tree-based methods, while achieving search effectiveness comparable to SOTA approximate NNS methods. These results underscore the potential of GTI for effective application in dynamic and evolving scenarios.

Centralised data management systems (e.g., data lakes) support queries over multi-source heterogeneous data. However, the query results from multiple sources commonly involve between-source conflicts, which makes query results unreliable and confusing and degrades the usability of centralised data management systems. Therefore, resolving the between-sourced conflicts is one of the most important problems for centralised data management systems. To solve it, many batch data fusion-based methods have been proposed, which require traversing all the data in the centralised data management systems and cause scalability and flexibility issues. To address these issues, this paper explores the problem of on-demand fusion queries, where the between-sourced conflicts are solved with only the query-related data; moreover, we propose an efficient on-demand fusion query framework, FusionQuery, which consists of a query stage and a fusion stage. In the query stage, we frame the heterogeneous data query problem as a knowledge graph matching problem and present a line graph-based method to accelerate it. In the fusion stage, we develop an Expectation Maximization-style algorithm to iteratively updates data veracity and source trustworthiness. Furthermore, we design an incremental estimation method of source trustworthiness to address the lack of sufficient observations. Extensive experiments on two real-world datasets demonstrate that FusionQuery outperforms state-of-the-art data fusion methods in terms of both effectiveness and efficiency.

The social network host has knowledge of the network structure and user characteristics and can earn a profit by providing merchants with viral marketing campaigns. We investigate the problem of host profit maximization by leveraging performance incentives and user flexibility. To incentivize the host's performance, we propose setting a desired influence threshold that would allow the host to receive full payment, with the possibility of a small bonus for exceeding the threshold. Unlike existing works that assume a user's choice is frozen once they are activated, we introduce the Dynamic State Switching model to capture "comparative shopping" behavior from an economic perspective, in which users have the flexibilities to change their minds about which product to adopt based on the accumulated influence and propaganda strength of each product. In addition, the incentivized cost of a user serving as an influence source is treated as a negative part of the host's profit. The host profit maximization problem is NP-hard, submodular, and non-monotone. To address this challenge, we propose an efficient greedy algorithm and devise a scalable version with an approximation guarantee to select the seed sets. As a side contribution, we develop two seed allocation algorithms to balance the distribution of adoptions among merchants with small profit sacrifice. Through extensive experiments on four real-world social networks, we demonstrate that our methods are effective and scalable.

Instant spatial keyword queries return the results as soon as users type in some characters instead of a complete keyword, which allow users to query the geo-textual data in a type-as-you-search manner. However, the existing methods of instant spatial keyword queries suffer from several limitations. For example, the existing methods do not consider the typographical errors of input keywords, and cannot be applied to the road networks. To overcome these limitations, in this paper, we propose a new query type, i.e., instant error-tolerant spatial keyword queries on road networks. To answer the queries efficiently, we present a framework, termed as Task, which consists of index component, query component, and update component. In the index component, we design a novel index called reverse 2-hop label based trie, which seamlessly integrates spatial and textual information for each vertex of the road network. Based on our proposed index, we devise efficient algorithms to progressively return and update the query results in the query component and update component, respectively. Finally, we conduct extensive experiments on real-world road networks to evaluate the performance of our presented Task. Empirical results show that our proposed index and algorithms are up to 1--2 orders of magnitude faster than the baseline.

Entity Matching (EM) aims to identify whether two tuples refer to the same real-world entity and is well-known to be labor-intensive. It is a prerequisite to anomaly detection, as comparing the attribute values of two matched tuples from two different datasets provides one effective way to detect anomalies. Existing EM approaches, due to insufficient feature discovery or error-prone inherent characteristics, are not able to achieve stable performance. In this paper, we present${{\sf CollaborEM}}$, a self-supervised entity matching framework via multi-features collaboration. It is capable of (i) obtaining reliable EM results with zero human annotations and (ii) discovering adequate tuples’ features in a fault-tolerant manner.${{\sf CollaborEM}}$consists of two phases, i.e., automatic label generation (ALG) and collaborative EM training (CEMT). In the first phase, ALG is proposed to generate a set of positive tuple pairs and a set of negative tuple pairs. ALG guarantees the high quality of the generated tuples, and hence ensures the training quality of the subsequent CEMT. In the second phase, CEMT is introduced to learn the matching signals by discovering graph features and sentence features of tuples collaboratively. Extensive experimental results over eight real-world EM benchmarks show that${{\sf CollaborEM}}$outperforms all the existing unsupervised EM approaches and is comparable or even superior to the state-of-the-art supervised EM methods.

Deploying database services on cloud systems has gained increasing popularity and has become a common practice in the industry. However, the complicated cloud environments make performance issues inevitable, which could violate the service level guarantee if not addressed in a timely manner. Among the various problems, anomalies in SQL queries are the most commonly reported sources that cause performance issues in database applications. These anomalous queries can be divided into High-impact SQLs (H-SQLs) and Root Cause SQLs (R-SQLs), representing the related SQLs that are correlated with the anomalies and the ones that are the root causes of the performance issue, respectively. In the presence of a large number of queries, to pinpoint the R-SQLs is far more difficult than to identify the H-SQLs. To address this challenge, we aim at automatically pinpointing the R-SQLs to resolve performance issues in cloud databases. This paper introduces PinSQL, an autonomous diagnosing system for Alibaba Cloud, which has four modules that are executed sequentially, including data collection and pre-processing, anomaly detection, root cause analysis, and repairing actions. First, the related performance metrics and query logs from monitored cloud database instances are collected and aggregated as the data sources. Then, based on these inputs, efficient anomaly detection is conducted in real-time. Upon the detection of an anomaly, the root cause SQLs are pinpointed through tracking the propagation chain of the involved SQLs. Finally, repairing actions are suggested and then executed on R-SQLs to address the anomalies. Extensive experiments on an Alibaba production system show that PinSQL can achieve an 80% accuracy for pinpointing the top-1 R-SQLs and successfully resolve the database performance issues resultantly.

Entity Matching (EM) aims to find data instances from different sources that refer to the same real-world entity. The existing EM techniques can be either costly or tailored for a specific data type. We present ZeroMatcher, a cost-off entity matching system, which supports (i) handling EM tasks with different data types, including relational tables and knowledge graphs; (ii) keeping its EM performance always competitive by enabling the sub-modules to be updated in a lightweight manner, thus reducing development costs; and (iii) performing EM without human annotations to further slash the labor costs. First, ZeroMatcher automatically suggests users a set of appropriate modules for EM according to the data types of the input datasets. Users could specify the modules for the subsequent EM process according to their preferences. Alternatively, users are able to customize the modules of ZeroMatcher. Then, the system proceeds to the EM task, where users can track the entire EM process and monitor the memory usage changes in real-time. When the EM process is completed, ZeroMatcher visualizes the EM results from different aspects to ease the understanding for users. Finally, ZeroMatcher provides EM results evaluation, enabling users to compare the effectiveness among different parameter settings.

With the increase of dirty data, data cleaning turns into a crux of data analysis. The accuracy limitation of the existing integrity constraints-based cleaning approaches results from insufficient rules. In this paper, we present a novel hybrid data cleaning framework on top of Markov logic networks (MLNs), termed as${\sf MLNClean}$, which is capable of learning instantiated rules to supplement the insufficient integrity constraints.${\sf MLNClean}$consists of two steps, i.e.,pre-processingandtwo-stage data cleaning. In the pre-processing step,${\sf MLNClean}$first infers a set of probable instantiated rules according to MLNs and then builds a two-layer MLN index structure to generate multiple data versions and facilitate the cleaning process. In the two-stage data cleaning step,${\sf MLNClean}$first presents a concept ofreliability scoreto clean errors within each data version separately, and afterward eliminates the conflict values among different data version using a novel concept offusion score. Considerable experimental results on both real and synthetic scenarios demonstrate the effectiveness of${\sf MLNClean}$in practice.

With the growth of dirty data, data cleaning turns into a crux of data analysis. In this paper, we propose a novel hybrid data cleaning framework, termed as MLNClean, which is capable of learning instantiated rules to supplement the insufficient integrity constraints. MLNClean consists of two steps, i.e., pre-processing and two-stage data cleaning. In the pre-processing step, MLNClean first infers a set of probable instantiated rules according to Markov logic network (MLN) and then builds a two-layer MLN index to generate multiple data versions and facilitate the cleaning process. In the two-stage data cleaning step, MLNClean first presents a concept of reliability score to clean errors within each data version separately, and then, it eliminates the conflict values among different data versions using a novel concept of fusion score. Considerable experimental results on both real and synthetic scenarios demonstrate the effectiveness of MLNClean.

Entity alignment (EA) is a prerequisite for enlarging the coverage of a unified knowledge graph. Previous EA approaches either restrain the performance due to inadequate information utilization or need labor-intensive pre-processing to get external or reliable information to perform the EA task. This paper proposes EASY, an effective end-to-end EA framework, which is able to (i) remove the labor-intensive pre-processing by fully discovering the name information provided by the entities themselves; and (ii) jointly fuse the features captured by the names of entities and the structural information of the graph to improve the EA results. Specifically, EASY first introduces NEAP, a highly effective name-based entity alignment procedure, to obtain an initial alignment that has reasonable accuracy and meanwhile does not require much memory consumption or any complex training process. Then, EASY invokes SRS, a novel structure-based refinement strategy, to iteratively correct the misaligned entities generated by NEAP to further enhance the entity alignment. Extensive experiments demonstrate the superiority of our proposed EASY with significant improvement against 13 existing state-of-the-art competitors.

Entity alignment (EA) aims to find equivalent entities in different knowledge graphs (KGs). Current EA approaches suffer from scalability issues, limiting their usage in real-world EA scenarios. To tackle this challenge, we propose LargeEA to align entities between large-scale KGs. LargeEA consists of two channels, i.e., structure channel and name channel. For the structure channel, we present METIS-CPS, a memory-saving mini-batch generation strategy, to partition large KGs into smaller mini-batches. LargeEA, designed as a general tool, can adopt any existing EA approach to learn entities' structural features within each mini-batch independently. For the name channel, we first introduce NFF, a name feature fusion method, to capture rich name features of entities without involving any complex training process; we then exploit a name-based data augmentation to generate seed alignment without any human intervention. Such design fits common real-world scenarios much better, as seed alignment is not always available. Finally, LargeEA derives the EA results by fusing the structural features and name features of entities. Since no widely-acknowledged benchmark is available for large-scale EA evaluation, we also develop a large-scale EA benchmark called DBP1M extracted from real-world KGs. Extensive experiments confirm the superiority of LargeEA against state-of-the-art competitors.

Data cleaning is a prerequisite to subsequent data analysis, and is know to often be time-consuming and labor-intensive. We present IHCS, a hybrid data cleaning system that integrates error detection and repair to contend effectively with multiple error types. In a preprocessing step that precedes the data cleaning, IHCS formats an input dataset to be cleaned, and transforms applicable data quality rules into a unified format. Then, an MLN index structure is formed according to the unified rules, enabling IHCS to handle multiple error types simultaneously. During the cleaning, IHCS first tackles abnormalities through an abnormal group process, and then, it generates multiple data versions based on the MLN index. Finally, IHCS eliminates conflicting values across the multiple versions, and derives the final unified clean data. A visual interface enables cleaning process monitoring and cleaning result analysis.