Kwan-Liu Ma

Time series anomaly detection is a critical machine learning task for numerous applications, such as finance, healthcare, and industrial systems. However, even high-performing models may exhibit potential issues such as biases, leading to unreliable outcomes and misplaced confidence. While model explanation techniques, particularly visual explanations, offer valuable insights by elucidating model attributions of their decision, many limitations still exist—They are primarily instance-based and not scalable across the dataset, and they provide one-directional information from the model to the human side, lacking a mechanism for users to address detected issues. To fulfill these gaps, we introduce HILAD , a novel framework designed to foster a dynamic and bidirectional collaboration between humans and AI for enhancing anomaly detection models in time series. Through our visual interface, HILAD empowers domain experts to detect, interpret, and correct unexpected model behaviors at scale. Our evaluation through user studies with two models and three time series datasets demonstrates the effectiveness of HILAD , which fosters a deeper model understanding, immediate corrective actions, and model reliability enhancement.

Time series forecasting plays a critical role in numerous real-world applications, such as finance, healthcare, transportation, and scientific computing. In recent years, deep learning has become a powerful tool for modeling complex temporal patterns and improving forecasting accuracy. This survey provides an overview of recent deep learning approaches for time series forecasting, involving various architectures including RNNs, CNNs, GNNs, transformers, large language models, MLP-based models, and diffusion models. We first identify key challenges in the field, such as temporal dependency, efficiency, and cross-variable dependency, which drive the development of forecasting techniques. Then, the general advantages and limitations of each architecture are discussed to contextualize their adaptation in time series forecasting. Furthermore, we highlight promising design trends like multi-scale modeling, decomposition, and frequency-domain techniques, which are shaping the future of the field. This paper serves as a compact reference for researchers and practitioners seeking to understand the current landscape and future trajectory of deep learning in time series forecasting.

In recent years, various summarization techniques have been proposed to address the increasing size of video data. However, most aim to compress information within the same modality, leading to inherent limitations in compression rates. Thus, to offset these effects, it is necessary to explore conversions to different modalities. In response, this study focuses on vignette illustrations, which are still-image illustrations that refine and visually express the narrative content of entertainment media, such as animated works or games. If video content can be transformed into vignette illustrations, it becomes possible to retain core visual information while achieving a significantly higher compression rate than conventional techniques. To this end, we propose the Video Image Generative Network, Transformed & Expanded (VigNette), a system that generates vignette illustrations from videos, supporting both semiautomated generation that reflects user preferences and automated generation without user input. Our experimental results demonstrate that VigNette can generate vignette illustrations suited to the content of a variety of anime videos. Furthermore, a user study confirmed that the system can visually represent the world perspective of each video. Further, our exploration into extending VigNette to include three-dimensional figure generations suggests such potential applications as the preservation of memorable scenes in a tangible form.

Understanding and distinguishing temporal patterns in time series data is essential for scientific discovery and decisionmaking. For example, in biomedical research, uncovering meaningful patterns in physiological signals can improve diagnosis, risk assessment, and patient outcomes. However, existing methods for time series pattern discovery face major challenges, including high computational complexity, limited interpretability, and difficulty in capturing meaningful temporal structures. To address these gaps, we introduce a novel learning framework that jointly trains two Transformer models using complementary time series representations: shapelet-based representations to capture localized temporal structures and traditional feature engineering to encode statistical properties. The learned shapelets serve as interpretable signatures that differentiate time series across classification labels. Additionally, we develop a visual analytics system-SigTime-with coordinated views to facilitate exploration of time series signatures from multiple perspectives, aiding in useful insights generation. We quantitatively evaluate our learning framework on eight publicly available datasets and one proprietary clinical dataset. Additionally, we demonstrate the effectiveness of our system through two usage scenarios along with the domain experts: one involving public ECG data and the other focused on preterm labor analysis.

Ensemble datasets are ever more prevalent in various scientific domains. In climate science, ensemble datasets are used to capture variability in projections under plausible future conditions including greenhouse and aerosol emissions. Each ensemble model run produces projections that are fundamentally similar yet meaningfully distinct. Understanding this variability among ensemble model runs and analyzing its magnitude and patterns is a vital task for climate scientists. In this paper, we present ClimateSOM, a visual analysis workflow that leverages a self-organizing map (SOM) and Large Language Models (LLMs) to support interactive exploration and interpretation of climate ensemble datasets. The workflow abstracts climate ensemble model runs—spatiotemporal time series—into a distribution over a 2D space that captures the variability among the ensemble model runs using a SOM. LLMs are integrated to assist in sensemaking of this SOM-defined 2D space, the basis for the visual analysis tasks. In all, ClimateSOM enables users to explore the variability among ensemble model runs, identify patterns, compare and cluster the ensemble model runs. To demonstrate the utility of ClimateSOM, we apply the workflow to an ensemble dataset of precipitation projections over California and the Northwestern United States. Furthermore, we conduct a short evaluation of our LLM integration, and conduct an expert review of the visual workflow and the insights from the case studies with six domain experts to evaluate our approach and its utility.

Understanding how students learn visualization skills is becoming increasingly crucial as generative AI transforms technical education. We present a systematic study examining how structured exposure to large language models via Observable’s AI Assist platform impacts data visualization education through a multiphase investigation across two universities. Our mixed-methods approach with 65 graduate students (32 data science and 33 computer science) revealed that structured generative AI exposure following constructivist learning principles enabled sustained engagement and tool adoption while maintaining pedagogical rigor. Through a structured multiphase study incorporating preassessments, intervention observations, detailed assignment reflections, and postintervention evaluation within the academic term constraints, we identified specific patterns in how students integrate generative AI into their visualization workflows. The results from our mixed-methods analysis suggest potential strategies for adapting visualization education to an AI-augmented future while preserving essential learning outcomes. We contribute practical frameworks for integrating generative AI tools into visualization curricula and evidence-based insights on scaffolding student learning with AI assistance, with initial evidence of sustained impact over a three-week period following instruction.

The tsNET algorithm utilizes t-SNE to compute high-quality graph drawings, preserving the neighborhood and clustering structure. We present three fast algorithms for reducing the time complexity of tsNET algorithm from O(nm) time to O(n log n) time and O(n) time. To reduce the runtime of tsNET, there are three components that need to be reduced: (C0) computation of high-dimensional probabilities, (C1) computation of KL divergence gradient, and (C2) entropy computation. Specifically, we reduce the overall runtime of tsNET, integrating our new fast approaches for C0 and C2 with fast t-SNE algorithms for C1. We first present O(n log n)-time BH-tsNET, based on (C0) new O(n)-time partial BFS-based high-dimensional probability computation and (C2) new O(n log n)-time quadtree-based entropy computation, integrated with (C1) O(n log n)-time quadtree-based KL divergence computation of BH-SNE. We next present faster O(n log n)-time FIt-tsNET, using (C0) O(n)-time partial BFS-based high-dimensional probability computation and (C2) quadtree-based O(n log n)-time entropy computation, integrated with (C1) O(n)-time interpolation-based KL divergence computation of FIt-SNE. Finally, we present the O(n)-time L-tsNET, integrating (C2) new O(n)-time FFT-accelerated interpolation-based entropy computation with (C0) O(n)-time partial BFS-based high-dimensional probability computation, and (C1) O(n)-time interpolation-based KL divergence computation of FIt-SNE. Extensive experiments using benchmark data sets confirm that BH-tsNET, FIt-tsNET, and L-tsNET outperform tsNET, running 93.5%, 96%, and 98.6% faster while computing similar quality drawings in terms of quality metrics (neighborhood preservation, stress, edge crossing, and shape-based metrics) and visual comparison. We also present a comparison between our algorithms and DRGraph, another dimension reduction-based graph drawing algorithm.

Financial literacy empowers individuals to make informed and effective financial decisions, improving their overall financial well-being and security. However, for many people understanding financial concepts can be daunting and only half of US adults are considered financially literate. Data visualization simplifies these concepts, making them accessible and engaging for learners of all ages. This systematic review analyzes 37 research papers exploring the use of data visualization and visual analytics in financial education and literacy enhancement. We classify these studies into five key areas: (1) the evolution of visualization use across time and space, (2) motivations for using visualization tools, (3) the financial topics addressed and instructional approaches used, (4) the types of tools and technologies applied, and (5) how the effectiveness of teaching interventions was evaluated. Furthermore, we identify research gaps and highlight opportunities for advancing financial literacy. Our findings offer practical insights for educators and professionals to effectively utilize or design visual tools for financial literacy.