Data wrangling (DW) is a fundamental step to prepare data for downstream mining tasks. Recent studies explore large language models (LLMs) to form a lightweight DW paradigm. Such studies typically require prompting an LLM with a DW task together with a few examples as task demonstrations (i.e., in-context learning). A problem yet to be explored is how to select the examples, to maximize task effectiveness given constraints on the size of the examples. To fill this gap, we introduce the constrained Shapley value (CSV), a tailored variant of the Shapley value with a constraint on the LLM prompt size, to guide example selection. We show that CSV has desirable properties in example importance estimation. Using CSV directly for LLM-based DW is still computationally intractable. We further propose activated contribution (ACSV) as an unbiased estimation for CSV and sample allocation algorithms with approximation guarantees. Empirical results show that, compared with DW examples manually selected by experts, CSV improves the effectiveness of LLMs for DW tasks including schema mapping, entity matching, error detection, and missing value imputation by 5.90% averagly in F1 score, demonstrating the general applicability of CSV for in-context learning example selection towards DW tasks.

Time series forecasting (TSF) is a prominent chal-lenge in data analytics, relevant to both scientific research and real-world industrial applications. The rapid increase in high-dimensional time series data has led researchers to develop numerous models capable of handling complex forecasting tasks across diverse scenarios. Nevertheless, selecting an appropriate model and optimizing its parameters-an issue known as the Combined Algorithm Selection and Hyperparameter optimization (CASH) problem-remains a significant challenge. It is worth investigating how to satisfy both accuracy and efficiency in selecting an optimal algorithm and its hyperparameter configu-ration for a given time series with minimal human intervention. Unfortunately, there is no such work in the field of TSF, which has been developed for more than a decade. Existing methods suffer low selection rate of optimal algorithms. Meanwhile, the TSF task is extremely algorithm-sensitive, and the prediction performance of different algorithms and hyperparameter settings on the same data varies greatly. In this paper, we propose a Proxy-Model-based meta-learning TSF-CASH approach named Auto- Tsf. In the offline training phase, Auto- Tsfextracts the historical experience based on the proxy models, which is used to guide the automatic algorithm selection in the online working phase. The historical experience extracted in the offline phase not only significantly reduces the time consumption for algorithm selection, but also the introduction of the proxy model enhances the optimal algorithm selection rate. Moreover, we propose an asynchronous parallel HPO method in the most time-consuming HPO stage, which further improves the efficiency of the whole TSF -CASH. The experimental results demonstrate that Auto- Tsfachieves SOTA in terms of performance and efficiency compared to existing CASH methods.

Unsupervised (a.k.a. Self-supervised) representation learning (URL) has emerged as a new paradigm for time series analysis, because it has the ability to learn generalizable time series representation beneficial for many downstream tasks without using labels that are usually difficult to obtain. Considering that existing approaches have limitations in the design of the representation encoder and the learning objective, we have proposed Contrastive Shapelet Learning (CSL), the first URL method that learns the general-purpose shapelet-based representation through unsupervised contrastive learning, and shown its superior performance in several analysis tasks, such as time series classification, clustering, and anomaly detection. In this paper, we develop TimeCSL, an end-to-end system that makes full use of the general and interpretable shapelets learned by CSL to achieve explorable time series analysis in a unified pipeline. We introduce the system components and demonstrate how users interact with TimeCSL to solve different analysis tasks in the unified pipeline, and gain insight into their time series by exploring the learned shapelets and representation.

Recent studies have shown great promise in unsupervised representation learning (URL) for multivariate time series, because URL has the capability in learning generalizable representation for many downstream tasks without using inaccessible labels. However, existing approaches usually adopt the models originally designed for other domains (e.g., computer vision) to encode the time series data and rely on strong assumptions to design learning objectives, which limits their ability to perform well. To deal with these problems, we propose a novel URL framework for multivariate time series by learning time-series-specific shapelet-based representation through a popular contrasting learning paradigm. To the best of our knowledge, this is the first work that explores the shapelet-based embedding in the unsupervised general-purpose representation learning. A unified shapelet-based encoder and a novel learning objective with multi-grained contrasting and multi-scale alignment are particularly designed to achieve our goal, and a data augmentation library is employed to improve the generalization. We conduct extensive experiments using tens of real-world datasets to assess the representation quality on many downstream tasks, including classification, clustering, and anomaly detection. The results demonstrate the superiority of our method against not only URL competitors, but also techniques specially designed for downstream tasks. Our code has been made publicly available at https://github.com/real2fish/CSL.