Cross-domain Text-to-SQL necessitates the capability of semantic parsers to generalize to unseen databases, thus simplifying the process of creating natural language interfaces for databases. The existing Text-to-SQL parser exhibits limitations in its adaptability to new databases, and its execution accuracy is not sufficient for building conversational applications, typically necessitating further fine-tuning for specific databases. In this paper, we introduce Chat2DB, a conversational system designed for database interactions that enhances parser capabilities, rendering them applicable in real-world contexts. Within Chat2DB, we implement an interactive schema-ranking agent that optimizes the performance of LMs-based parsers cost-effectively. We further propose an adaptive retraining stage to allow trained Text-to-SQL parsers to quickly adapt to the target database. Experimental evaluations were conducted to validate the performance of the key components of Chat2DB. In the demonstration, we showcase the interactive visualization interface of Chat2DB to achieve more accurate querying of databases by natural language.

Multi-modal time series data is common in web technologies like the Internet of Things (IoT). Existing methods for multi-modal time series representation learning aim to disentangle the modality-shared and modality-specific latent variables. Although achieving notable performances on downstream tasks, they usually assume an orthogonal latent space. However, the modality-specific and modality-shared latent variables might be dependent on real-world scenarios. Therefore, we propose a general generation process, where the modality-shared and modality-specific latent variables are dependent, and further develop a Multi-modAl TEmporal Disentanglement (MATE) model. Specifically, our MATE model is built on a temporally variational inference architecture with the modality-shared and modality-specific prior networks for the disentanglement of latent variables. Furthermore, we establish identifiability results to show that the extracted representation is disentangled. More specifically, we first achieve the subspace identifiability for modality-shared and modality-specific latent variables by leveraging the pairing of multi-modal data. Then we establish the component-wise identifiability of modality-specific latent variables by employing sufficient changes of historical latent variables. Extensive experimental studies on 12 datasets show a general improvement in different downstream tasks, highlighting the effectiveness of our method in real-world scenarios.

Contemporary datasets sourced from the web often adopt a multiview format, collecting data from diverse sources, domains, or modules.Existing methodologies employed to analyze such datasets frequently overlook or inaccurately allocate the view-weights, pivotal metrics reflecting each view's significance.This work introduces EVA-MVC, a simple yet effective algorithm designed for Equitable View-weight Allocation (EVA) seamlessly integrated with arbitrary Multi-view Clustering (MVC) methods.Within the EVA module, we establish theoretical connections between view supplementarity and Multi-view Subspace Learning (MSL), leading to the partition of views into View Communities (VCs) based on these foundational principles.These VCs exhibit internal supplementarity similarities, facilitating Equitable View-weights Allocation through VCspecific MSL.The proposed EVA process precedes and operates independently of traditional or SOTA MVC approaches, requiring no additional processing or specialized design, making it an ideal preprocessing step for MVC applications.Through comprehensive evaluations across diverse multi-view datasets, our findings reveal that our EVA significantly enhances the effectiveness of mainstream MVC frameworks, resulting in a notable performance improvement.

Learning Granger causality from event sequences has important applications in various scenarios. Many methods have been developed based on Hawkes process with a stationarity assumption. However, these methods often fail in real-world scenarios due to violating the stationarity assumption, as an event sequence can be generated under different states at varying times. Although some work tries to model non-stationarity by searching for best segmentation, they still suffer from the lack of robustness and identification guarantee. An intuitive solution is to model the non-stationary generation process in a unified probabilistic generative framework. This presents two significant challenges: how to model the generation process considering both the stationarity of each subsequence and the non-stationarity among the subsequences, and how to identify the Granger causality. To address these challenges, we devise State Hawkes Processes (StateHPs). For the first challenge, StateHPs formulates the state assignments of each subsequence as a Dirichlet distribution and each state as a Hawkes process. For the second challenge, StateHPs introduces a variational Expectation-Maximization algorithm to identify the Granger causal graph. We also develop the identification theories for StateHPs. On real-world data, StateHPs achieves 35.5%, 33.9%, and 36.7% improvement among F1, Precision, and Recall metrics compared to the SOTA baselines.

Mining temporal patterns from user behaviors has long been investigated, but most of the existing work centers on single-type user–item interactions, such as purchase or click, which fails to take advantage of the user’s diversified interests revealed by various types of behavior. However, capturing patterns from different behavior sequences and modeling the complex inter-correlation between them are non-trivial tasks, as the high sparsity of type-related interactions, multi-seasonality of individual behaviors, and time-variant dependency of multi-type activities make it really challenging. To address these challenges, we propose a novel framework that aims to model the M ulti-Seasonal M ulti-Behavior Dep endencies (MMDep) both within and across the multi-type behavior sequences. In the proposed model, an item co-occurrence matrix factorization strategy is introduced to alleviate the sparsity issue in type-related behavior sequences. And a temporal dependency module that incorporates multi-scale EMA mechanism is utilized to capture the multi-seasonal dependencies within individual sequences. Moreover, a cross-behavior dependency module is employed to learn the time-variant dependency among different behaviors. Extensive experiments on three real-world datasets demonstrate that the proposed MMDep performs significantly better than the state-of-the-art baselines. And it may provide some new insights and tools on how to leverage multi-behavior data for better temporal recommendation.

In the domain of Multi-view Subspace Clustering (MSC) in Latent Embedding Space (LES), existing methods aim to capture and leverage critical multi-view information by mapping it into a low-dimensional LES. However, several aspects can be further improved: (i) Fusion Strategy: Existing methods adopt either early fusion or late fusion to integrate multi-view information, limiting the effectiveness of the fusion. (ii) Diversity: Current methods often overlook the inherent diversity in the multi-view data by focusing on a single LES. (iii) Efficiency: LES-based methods exhibit high computational complexity, with cubic time and quadratic space requirements based on the number of samples. To address these issues, we propose a novel framework called MSC-DOLES (Multi-view Subspace Clustering in Diverse Orthogonal Latent Embedding Spaces), a novel framework designed to tackle these challenges. MSC-DOLES incorporates a two-stage fusion approach that generates and learns from multiple LES to maximize cross-view diversity. Orthogonality constraints on individual LES ensure view-internal diversity, resulting in a set of Diverse Orthogonal Latent Embedding Spaces (DOLES). The DOLES are then fused into a consensus anchor graph using learnable anchors. The final clustering is induced by partitioning the obtained graph without pre-processing. We develop an eight-step optimization algorithm for MSC-DOLES, which exhibits nearly linear time and space complexities relative to the number of samples. Extensive experiments demonstrate the superiority of MSC-DOLES over state-of-the-art methods.

Recent years have witnessed tremendous interest in deep learning on graph-structured data. Due to the high cost of collecting labeled graph-structured data, domain adaptation is important to supervised graph learning tasks with limited samples. However, current graph domain adaptation methods are generally adopted from traditional domain adaptation tasks, and the properties of graph-structured data are not well utilized. For example, the observed social networks on different platforms are controlled not only by the different crowds or communities but also by domain-specific policies and background noise. Based on these properties in graph-structured data, we first assume that the graph-structured data generation process is controlled by three independent types of latent variables, i.e., the semantic latent variables, the domain latent variables, and the random latent variables. Based on this assumption, we propose a disentanglement-based unsupervised domain adaptation method for the graph-structured data, which applies variational graph auto-encoders to recover these latent variables and disentangles them via three supervised learning modules. Extensive experimental results on two real-world datasets in the graph classification task reveal that our method not only significantly outperforms the traditional domain adaptation methods and the disentangled-based domain adaptation methods but also outperforms the state-of-the-art graph domain adaptation algorithms. The code is available at https://github.com/rynewu224/GraphDA .

Estimating causal effects from observational network data is a significant but challenging problem. Existing works in causal inference for observational network data lack an analysis of the generalization bound, which can theoretically provide support for alleviating the complex confounding bias and practically guide the design of learning objectives in a principled manner. To fill this gap, we derive a generalization bound for causal effect estimation in network scenarios by exploiting 1) the reweighting schema based on joint propensity score and 2) the representation learning schema based on Integral Probability Metric (IPM). We provide two perspectives on the generalization bound in terms of reweighting and representation learning, respectively. Motivated by the analysis of the bound, we propose a weighting regression method based on the joint propensity score augmented with representation learning. Extensive experimental studies on two real-world networks with semi-synthetic data demonstrate the effectiveness of our algorithm.

Data-driven models are becoming essential parts in modern mechanical systems, commonly used to capture the behavior of various equipment and varying environmental characteristics. Despite the advantages of these data-driven models on excellent adaptivity to high dynamics and aging equipment, they are usually hungry for massive labels, mostly contributed by human engineers at a high cost. Fortunately, domain adaptation enhances the model generalization by utilizing the labeled source data and the unlabeled target data. However, the mainstream domain adaptation methods cannot achieve ideal performance on time series data, since they assume that the conditional distributions are equal. This assumption works well in the static data but is inapplicable for the time series data. Even the first-order Markov dependence assumption requires the dependence between any two consecutive time steps. In this article, we assume that the causal mechanism is invariant and present our Causal Mechanism Transfer Network (CMTN) for time series domain adaptation. By capturing causal mechanisms of time series data, CMTN allows the data-driven models to exploit existing data and labels from similar systems, such that the resulting model on a new system is highly reliable even with limited data. We report our empirical results and lessons learned from two real-world case studies, on chiller plant energy optimization and boiler fault detection, which outperform the existing state-of-the-art method.

Identification of causal direction between a causal-effect pair from observed data has recently attracted much attention. Various methods based on functional causal models have been proposed to solve this problem, by assuming the causal process satisfies some (structural) constraints and showing that the reverse direction violates such constraints. The nonlinear additive noise model has been demonstrated to be effective for this purpose, but the model class does not allow any confounding or intermediate variables between a cause pair–even if each direct causal relation follows this model. However, omitting the latent causal variables is frequently encountered in practice. After the omission, the model does not necessarily follow the model constraints. As a consequence, the nonlinear additive noise model may fail to correctly discover causal direction. In this work, we propose a confounding cascade nonlinear additive noise model to represent such causal influences–each direct causal relation follows the nonlinear additive noise model but we observe only the initial cause and final effect. We further propose a method to estimate the model, including the unmeasured confounding and intermediate variables, from data under the variational auto-encoder framework. Our theoretical results show that with our model, the causal direction is identifiable under suitable technical conditions on the data generation process. Simulation results illustrate the power of the proposed method in identifying indirect causal relations across various settings, and experimental results on real data suggest that the proposed model and method greatly extend the applicability of causal discovery based on functional causal models in nonlinear cases.

Massive data streams from sensors in Internet of Things (IoT) and smart devices with Global Positioning System (GPS) are now flooding to database systems for further processing and analysis. The capability of real-time retrieval from both fresh and historical data turns out to be the key enabler to the real world applications in smart manufacturing and smart city utilizing these data streams. In this paper, we present a simple and effective distributed solution to achieve millions of tuple insertions per second and ad-hoc temporal range query processing in milliseconds. To this end, we propose a new data partitioning scheme that takes advantage of the workload characteristics and avoids expensive global data merging. Furthermore, to resolve the throughput bottleneck, we adopt a template-based index method to skip unnecessary index structure adjustments over the relatively stable distribution of incoming tuples. To parallelize data insertion and query processing, we propose an efficient dispatching mechanism and effective load balancing strategies to fully utilize computational resources in a workload-aware manner. On both synthetic and real workloads, our solution consistently outperforms state-of-the-art open-source systems by at least an order of magnitude.

The prosperity of mobile social network and location-based services, e.g., Uber, is backing the explosive growth of spatial temporal streams on the Internet. It raises new challenges to the underlying data store system, which is supposed to support extremely high-throughput trajectory insertion and low-latency querying with spatial and temporal constraints. State-of-the-art solutions, e.g., HBase, do not render satisfactory performance, due to the high overhead on index update. In this demonstration, we present DITIR, our new system prototype tailored to efficiently processing temporal and spacial queries over historical data as well as latest updates. Our system provides better performance guarantee, by physically partitioning the incoming data tuples on their arrivals and exploiting a template-based insertion schema, to reach the desired ingestion throughput. Load balancing mechanism is also introduced to DITIR, by using which the system is capable of achieving reliable performance against workload dynamics. Our demonstration shows that DITIR supports over 1 million tuple insertions in a second, when running on a 10-node cluster. It also significantly outperforms HBase by 7 times on ingestion throughput and 5 times faster on query latency.

Drug-target interaction (DTI) provides novel insights about the genomic drug discovery, and is a critical technique to drug discovery. Recently, researchers try to incorporate different information about drugs and targets for prediction. However, the heterogeneous and high-dimensional data poses huge challenge to existing machine learning methods. In the last few years, extensive research efforts have been devoted to the utilization of manifold property on high dimensional data, e.g. dimension reduction methods preserving local structures of the manifolds. Motivated by the successes of these studies, we propose a general framework incorporating both manifold structures and known interaction/non-interaction information to predict the drug-target interactions. To overcome the challenges of domain scaling and information inconsistency, we formulate the problem with Semidefinite Programming (SDP), including new constraints to improve the robustness of the learning procedure. A variety of optimization techniques are also designed to enhance the scalability of the problem solver. Effectiveness of the method is evaluated by experiments on the benchmark dataset. Compared with state-of-the-art methods, the proposed methods generate much more accurate drug-target interaction prediction.

In previous studies, association rules have been proven to be useful in classification problems over high dimensional gene expression data. However, due to the nature of such data sets, it is often the case that millions of rules can be derived such that many of them are covered by exactly the same set of training tuples and thus have exactly the same support and confidence. Ranking and selecting useful rules from such equivalent rule groups remain an interesting and unexplored problem. In this paper, we look at two interestingness measures for ranking the interestingness of rules within equivalent rule group: Max-Subrule-Conf and Min-Subrule-Conf. Based on these interestingness measures, an incremental Apriori-like algorithm is designed to select more interesting rules from the lower bound rules of the group. Moreover, we present an improved classification model to fully exploit the potential of the selected rules. Our empirical studies on our proposed methods over five gene expression data sets show that our proposals improve both the efficiency and effectiveness of the rule extraction and classifier construction over gene expression data sets.

The skyline of a d-dimensional dataset consists of all points not dominated by others. The incorporation of the skyline operator into practical database systems necessitates an efficient and effective cardinality estimation module. However, existing theoretical work on this problem is limited to the case where all d dimensions are independent of each other, which rarely holds for real datasets. The state of the art Log Sampling (LS) technique simply applies theoretical results for independent dimensions to non-independent data anyway, sometimes leading to large estimation errors. To solve this problem, we propose a novel Kernel-Based (KB) approach that approximates the skyline cardinality with nonparametric methods. Extensive experiments with various real datasets demonstrate that KB achieves high accuracy, even in cases where LS fails. At the same time, despite its numerical nature, the efficiency of KB is comparable to that of LS. Furthermore, we extend both LS and KB to the k-dominant skyline, which is commonly used instead of the conventional skyline for high-dimensional data.