Multi-agent workflows have become an effective strategy for tackling complicated tasks by decomposing them into multiple sub-tasks and assigning them to specialized agents. However, designing optimal workflows remains challenging due to the vast and intricate design space. Current practices rely heavily on the intuition and expertise of practitioners, often resulting in design fixation or an unstructured, time-consuming exploration of trial-and-error. To address these challenges, this work introduces FLOWFORGE, an interactive visualization tool to facilitate the creation of multi-agent workflow through i) a structured visual exploration of the design space and ii) in-situ guidance informed by established design patterns. Based on formative studies and literature review, FLOWFORGE organizes the workflow design process into three hierarchical levels (i.e., task planning, agent assignment, and agent optimization), ranging from abstract to concrete. This structured visual exploration enables users to seamlessly move from high-level planning to detailed design decisions and implementations, while comparing alternative solutions across multiple performance metrics. Additionally, drawing from established workflow design patterns, FLOWFORGE provides context-aware, in-situ suggestions at each level as users navigate the design space, enhancing the workflow creation process with practical guidance. Use cases and user studies demonstrate the usability and effectiveness of FLOWFORGE, while also yielding valuable insights into how practitioners explore design spaces and leverage guidance during workflow development.

Graph Neural Networks (GNNs) have achieved significant success across various applications. However, their complex structures and inner workings can be challenging for non-AI experts to understand. To address this issue, this study presents GNN101, an educational visualization tool for interactive learning of GNNs. GNN101 introduces a set of animated visualizations that seamlessly integrates mathematical formulas with visualizations via multiple levels of abstraction, including a model overview, layer operations, and detailed calculations. Users can easily switch between two complementary views: a node-link view that offers an intuitive understanding of the graph data, and a matrix view that provides a space-efficient and comprehensive overview of all features and their transformations across layers. GNN101 was designed and developed based on close collaboration with four GNN experts and deployment in three GNN-related courses. We demonstrated the usability and effectiveness of GNN101 via use cases and user studies with both GNN teaching assistants and students. To ensure broad educational access, GNN101 is developed through modern web technologies and available directly in web browsers without requiring any installations.

While many visualizations are built for domain users (e.g., biologists, machine learning developers), understanding how visualizations are used in the domain has long been a challenging task. Previous research has relied on either interviewing a limited number of domain users or reviewing relevant application papers in the visualization community, neither of which provides comprehensive insight into visualizations "in the wild" of a specific domain. This paper aims to fill this gap by examining the potential of using Large Language Models (LLM) to analyze visualization usage in domain literature. We use high-dimension (HD) data visualization in sing-cell transcriptomics as a test case, analyzing 1,203 papers that describe 2,056 HD visualizations with highly specialized domain terminologies (e.g., biomarkers, cell lineage). To facilitate this analysis, we introduce a human-in-the-loop LLM workflow that can effectively analyze a large collection of papers and translate domain-specific terminology into standardized data and task abstractions. Instead of relying solely on LLMs for end-to-end analysis, our workflow enhances analytical quality through 1) integrating image processing and traditional NLP methods to prepare well-structured inputs for three targeted LLM subtasks (i.e., translating domain terminology, summarizing analysis tasks, and performing categorization), and 2) establishing checkpoints for human involvement and validation throughout the process. The analysis results, validated with expert interviews and a test set, revealed three often overlooked aspects in HD visualization: trajectories in HD spaces, inter-cluster relationships, and dimension clustering. This research provides a stepping stone for future studies seeking to use LLMs to bridge the gap between visualization design and domain-specific usage.

Dimensionality reduction is used as an important tool for unraveling the complexities of high-dimensional datasets in many fields of science, such as cell biology, chemical informatics, and physics. Visualizations of the dimensionally-reduced data enable scientists to delve into the intrinsic structures of their datasets and align them with established hypotheses. Visualization researchers have thus proposed many dimensionality reduction methods and interactive systems designed to uncover latent structures. At the same time, different scientific domains have formulated guidelines or common workflows for using dimensionality reduction techniques and visualizations for their respective fields. In this work, we present a critical analysis of the usage of dimensionality reduction in scientific domains outside of computer science. First, we conduct a bibliometric analysis of 21,249 academic publications that use dimensionality reduction to observe differences in the frequency of techniques across fields. Next, we conduct a survey of a 71-paper sample from four fields: biology, chemistry, physics, and business. Through this survey, we uncover common workflows, processes, and usage patterns, including the mixed use of confirmatory data analysis to validate a dataset and projection method and exploratory data analysis to then generate more hypotheses. We also find that misinterpretations and inappropriate usage is common, particularly in the visual interpretation of the resulting dimensionally reduced view. Lastly, we compare our observations with recent works in the visualization community in order to match work within our community to potential areas of impact outside our community. By comparing the usage found within scientific fields to the recent research output of the visualization community, we offer both validation of the progress of visualization research into dimensionality reduction and a call for action to produce techniques that meet the needs of scientific users.

The increasing reliance on Large Language Models (LLMs) for health information seeking can pose severe risks due to the potential for misinformation and the complexity of these topics. This paper introduces KnowNet a visualization system that integrates LLMs with Knowledge Graphs (KG) to provide enhanced accuracy and structured exploration. Specifically, for enhanced accuracy, KnowNet extracts triples (e.g., entities and their relations) from LLM outputs and maps them into the validated information and supported evidence in external KGs. For structured exploration, KnowNet provides next-step recommendations based on the neighborhood of the currently explored entities in KGs, aiming to guide a comprehensive understanding without overlooking critical aspects. To enable reasoning with both the structured data in KGs and the unstructured outputs from LLMs, KnowNet conceptualizes the understanding of a subject as the gradual construction of graph visualization. A progressive graph visualization is introduced to monitor past inquiries, and bridge the current query with the exploration history and next-step recommendations. We demonstrate the effectiveness of our system via use cases and expert interviews.

., t-SNE) but suffer from a lack of interpretability. While previous studies employed disentangled representation learning (DRL) to enable more interpretable exploration, they often overlooked the potential mismatches between the concepts of humans and the semantic dimensions learned by DRL. To address this issue, we propose Drava, a visual analytics system that supports users in 1) relating the concepts of humans with the semantic dimensions of DRL and identifying mismatches, 2) providing feedback to minimize the mismatches, and 3) obtaining data insights from concept-driven exploration. Drava provides a set of visualizations and interactions based on visual piles to help users understand and refine concepts and conduct concept-driven exploration. Meanwhile, Drava employs a concept adaptor model to fine-tune the semantic dimensions of DRL based on user refinement. The usefulness of Drava is demonstrated through application scenarios and experimental validation.

Reference-based cell-type annotation can significantly reduce time and effort in single-cell analysis by transferring labels from a previously-annotated dataset to a new dataset. However, label transfer by end-to-end computational methods is challenging due to the entanglement of technical (e.g., from different sequencing batches or techniques) and biological (e.g., from different cellular microenvironments) variations, only the first of which must be removed. To address this issue, we propose Polyphony, an interactive transfer learning (ITL) framework, to complement biologists' knowledge with advanced computational methods. Polyphony is motivated and guided by domain experts' needs for a controllable, interactive, and algorithm-assisted annotation process, identified through interviews with seven biologists. We introduce anchors, i.e., analogous cell populations across datasets, as a paradigm to explain the computational process and collect user feedback for model improvement. We further design a set of visualizations and interactions to empower users to add, delete, or modify anchors, resulting in refined cell type annotations. The effectiveness of this approach is demonstrated through quantitative experiments, two hypothetical use cases, and interviews with two biologists. The results show that our anchor-based ITL method takes advantage of both human and machine intelligence in annotating massive single-cell datasets.

Graph Neural Networks (GNNs) aim to extend deep learning techniques to graph data and have achieved significant progress in graph analysis tasks (e.g., node classification) in recent years. However, similar to other deep neural networks like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), GNNs behave like a black box with their details hidden from model developers and users. It is therefore difficult to diagnose possible errors of GNNs. Despite many visual analytics studies being done on CNNs and RNNs, little research has addressed the challenges for GNNs. This paper fills the research gap with an interactive visual analysis tool, GNNLens, to assist model developers and users in understanding and analyzing GNNs. Specifically, Parallel Sets View and Projection View enable users to quickly identify and validate error patterns in the set of wrong predictions; Graph View and Feature Matrix View offer a detailed analysis of individual nodes to assist users in forming hypotheses about the error patterns. Since GNNs jointly model the graph structure and the node features, we reveal the relative influences of the two types of information by comparing the predictions of three models: GNN, Multi-Layer Perceptron (MLP), and GNN Without Using Features (GNNWUF). Two case studies and interviews with domain experts demonstrate the effectiveness of GNNLens in facilitating the understanding of GNN models and their errors.

Interpretation of genomics data is critically reliant on the application of a wide range of visualization tools. A large number of visualization techniques for genomics data and different analysis tasks pose a significant challenge for analysts: which visualization technique is most likely to help them generate insights into their data? Since genomics analysts typically have limited training in data visualization, their choices are often based on trial and error or guided by technical details, such as data formats that a specific tool can load. This approach prevents them from making effective visualization choices for the many combinations of data types and analysis questions they encounter in their work. Visualization recommendation systems assist non-experts in creating data visualization by recommending appropriate visualizations based on the data and task characteristics. However, existing visualization recommendation systems are not designed to handle domain-specific problems. To address these challenges, we designed GenoREC, a novel visualization recommendation system for genomics. GenoREC enables genomics analysts to select effective visualizations based on a description of their data and analysis tasks. Here, we present the recommendation model that uses a knowledge-based method for choosing appropriate visualizations and a web application that enables analysts to input their requirements, explore recommended visualizations, and export them for their usage. Furthermore, we present the results of two user studies demonstrating that GenoREC recommends visualizations that are both accepted by domain experts and suited to address the given genomics analysis problem. All supplemental materials are available at https://osf.io/y73pt/.

Whether AI explanations can help users achieve specific tasks efficiently (i.e., usable explanations) is significantly influenced by their visual presentation. While many techniques exist to generate explanations, it remains unclear how to select and visually present AI explanations based on the characteristics of domain users. This paper aims to understand this question through a multidisciplinary design study for a specific problem: explaining graph neural network (GNN) predictions to domain experts in drug repurposing, i.e., reuse of existing drugs for new diseases. Building on the nested design model of visualization, we incorporate XAI design considerations from a literature review and from our collaborators' feedback into the design process. Specifically, we discuss XAI-related design considerations for usable visual explanations at each design layer: target user, usage context, domain explanation, and XAI goal at the domain layer; format, granularity, and operation of explanations at the abstraction layer; encodings and interactions at the visualization layer; and XAI and rendering algorithm at the algorithm layer. We present how the extended nested model motivates and informs the design of DrugExplorer, an XAI tool for drug repurposing. Based on our domain characterization, DrugExplorer provides path-based explanations and presents them both as individual paths and meta-paths for two key XAI operations, why and what else. DrugExplorer offers a novel visualization design called MetaMatrix with a set of interactions to help domain users organize and compare explanation paths at different levels of granularity to generate domain-meaningful insights. We demonstrate the effectiveness of the selected visual presentation and DrugExplorer as a whole via a usage scenario, a user study, and expert interviews. From these evaluations, we derive insightful observations and reflections that can inform the design of XAI visualizations for other scientific applications.

The combination of diverse data types and analysis tasks in genomics has resulted in the development of a wide range of visualization techniques and tools. However, most existing tools are tailored to a specific problem or data type and offer limited customization, making it challenging to optimize visualizations for new analysis tasks or datasets. To address this challenge, we designed Gosling-a grammar for interactive and scalable genomics data visualization. Gosling balances expressiveness for comprehensive multi-scale genomics data visualizations with accessibility for domain scientists. Our accompanying JavaScript toolkit called Gosling.js provides scalable and interactive rendering. Gosling.js is built on top of an existing platform for web-based genomics data visualization to further simplify the visualization of common genomics data formats. We demonstrate the expressiveness of the grammar through a variety of real-world examples. Furthermore, we show how Gosling supports the design of novel genomics visualizations. An online editor and examples of Gosling.js, its source code, and documentation are available at https://gosling.js.org.

Inspired by the great success of machine learning (ML), researchers have applied ML techniques to visualizations to achieve a better design, development, and evaluation of visualizations. This branch of studies, known as ML4VIS, is gaining increasing research attention in recent years. To successfully adapt ML techniques for visualizations, a structured understanding of the integration of ML4VIS is needed. In this article, we systematically survey 88 ML4VIS studies, aiming to answer two motivating questions: "what visualization processes can be assisted by ML?" and "how ML techniques can be used to solve visualization problems? "This survey reveals seven main processes where the employment of ML techniques can benefit visualizations: Data Processing4VIS, Data-VIS Mapping, Insight Communication, Style Imitation, VIS Interaction, VIS Reading, and User Profiling. The seven processes are related to existing visualization theoretical models in an ML4VIS pipeline, aiming to illuminate the role of ML-assisted visualization in general visualizations. Meanwhile, the seven processes are mapped into main learning tasks in ML to align the capabilities of ML with the needs in visualization. Current practices and future opportunities of ML4VIS are discussed in the context of the ML4VIS pipeline and the ML-VIS mapping. While more studies are still needed in the area of ML4VIS, we hope this article can provide a stepping-stone for future exploration. A web-based interactive browser of this survey is available at https://ml4vis.github.io.

A growing number of longitudinal cohort studies are generating data with extensive patient observations across multiple timepoints. Such data offers promising opportunities to better understand the progression of diseases. However, these observations are usually treated as general events in existing visual analysis tools. As a result, their capabilities in modeling disease progression are not fully utilized. To fill this gap, we designed and implemented ThreadStates, an interactive visual analytics tool for the exploration of longitudinal patient cohort data. The focus of ThreadStates is to identify the states of disease progression by learning from observation data in a human-in-the-loop manner. We propose a novel Glyph Matrix design and combine it with a scatter plot to enable seamless identification, observation, and refinement of states. The disease progression patterns are then revealed in terms of state transitions using Sankey-based visualizations. We employ sequence clustering techniques to find patient groups with distinctive progression patterns, and to reveal the association between disease progression and patient-level features. The design and development were driven by a requirement analysis and iteratively refined based on feedback from domain experts over the course of a 10-month design study. Case studies and expert interviews demonstrate that ThreadStates can successively summarize disease states, reveal disease progression, and compare patient groups.

In this paper, we propose SineStream, a new variant of streamgraphs that improves their readability by minimizing sine illusion effects. Such effects reflect the tendency of humans to take the orthogonal rather than the vertical distance between two curves as their distance. In SineStream, we connect the readability of streamgraphs with minimizing sine illusions and by doing so provide a perceptual foundation for their design. As the geometry of a streamgraph is controlled by its baseline (the bottom-most curve) and the ordering of the layers, we re-interpret baseline computation and layer ordering algorithms in terms of reducing sine illusion effects. For baseline computation, we improve previous methods by introducing a Gaussian weight to penalize layers with large thickness changes. For layer ordering, three design requirements are proposed and implemented through a hierarchical clustering algorithm. Quantitative experiments and user studies demonstrate that SineStream improves the readability and aesthetics of streamgraphs compared to state-of-the-art methods.

In this paper, we present a visual analytics tool for enabling hypothesis-based evaluation of machine learning (ML) models. We describe a novel ML-testing framework that combines the traditional statistical hypothesis testing (commonly used in empirical research) with logical reasoning about the conclusions of multiple hypotheses. The framework defines a controlled configuration for testing a number of hypotheses as to whether and how some extra information about a "concept" or "feature" may benefit or hinder an ML model. Because reasoning multiple hypotheses is not always straightforward, we provide HypoML as a visual analysis tool, with which, the multi-thread testing results are first transformed to analytical results using statistical and logical inferences, and then to a visual representation for rapid observation of the conclusions and the logical flow between the testing results and hypotheses. We have applied HypoML to a number of hypothesized concepts, demonstrating the intuitive and explainable nature of the visual analysis.

The growing use of automated decision-making in critical applications, such as crime prediction and college admission, has raised questions about fairness in machine learning. How can we decide whether different treatments are reasonable or discriminatory? In this paper, we investigate discrimination in machine learning from a visual analytics perspective and propose an interactive visualization tool, DiscriLens, to support a more comprehensive analysis. To reveal detailed information on algorithmic discrimination, DiscriLens identifies a collection of potentially discriminatory itemsets based on causal modeling and classification rules mining. By combining an extended Euler diagram with a matrix-based visualization, we develop a novel set visualization to facilitate the exploration and interpretation of discriminatory itemsets. A user study shows that users can interpret the visually encoded information in DiscriLens quickly and accurately. Use cases demonstrate that DiscriLens provides informative guidance in understanding and reducing algorithmic discrimination.

This paper presents an authoring environment for augmenting static visualizations with virtual content in augmented reality.Augmenting static visualizations can leverage the best of both physical and digital worlds, but its creation currently involves different tools and devices, without any means to explicitly design and debug both static and virtual content simultaneously. To address these issues, we design an environment that seamlessly integrates all steps of a design and deployment workflow through its main features: i) an extension to Vega, ii) a preview, and iii) debug hints that facilitate valid combinations of static and augmented content. We inform our design through a design space with four ways to augment static visualizations. We demonstrate the expressiveness of our tool through examples, including books, posters, projections, wall-sized visualizations. A user study shows high user satisfaction of our environment and confirms that participants can create augmented visualizations in an average of 4.63 minutes.

Recent advances in mobile augmented reality (AR) techniques have shed new light on personal visualization for their advantages of fitting visualization within personal routines, situating visualization in a real-world context, and arousing users' interests. However, enabling non-experts to create data visualization in mobile AR environments is challenging given the lack of tools that allow in-situ design while supporting the binding of data to AR content. Most existing AR authoring tools require working on personal computers or manually creating each virtual object and modifying its visual attributes. We systematically study this issue by identifying the specificity of AR glyph-based visualization authoring tool and distill four design considerations. Following these design considerations, we design and implement MARVisT, a mobile authoring tool that leverages information from reality to assist non-experts in addressing relationships between data and virtual glyphs, real objects and virtual glyphs, and real objects and data. With MARVisT, users without visualization expertise can bind data to real-world objects to create expressive AR glyph-based visualizations rapidly and effortlessly, reshaping the representation of the real world with data. We use several examples to demonstrate the expressiveness of MARVisT. A user study with non-experts is also conducted to evaluate the authoring experience of MARVisT.

Designers need to consider not only perceptual effectiveness but also visual styles when creating an infographic. This process can be difficult and time consuming for professional designers, not to mention non-expert users, leading to the demand for automated infographics design. As a first step, we focus on timeline infographics, which have been widely used for centuries. We contribute an end-to-end approach that automatically extracts an extensible timeline template from a bitmap image. Our approach adopts a deconstruction and reconstruction paradigm. At the deconstruction stage, we propose a multi-task deep neural network that simultaneously parses two kinds of information from a bitmap timeline: 1) the global information, i.e., the representation, scale, layout, and orientation of the timeline, and 2) the local information, i.e., the location, category, and pixels of each visual element on the timeline. At the reconstruction stage, we propose a pipeline with three techniques, i.e., Non-Maximum Merging, Redundancy Recover, and DL GrabCut, to extract an extensible template from the infographic, by utilizing the deconstruction results. To evaluate the effectiveness of our approach, we synthesize a timeline dataset (4296 images) and collect a real-world timeline dataset (393 images) from the Internet. We first report quantitative evaluation results of our approach over the two datasets. Then, we present examples of automatically extracted templates and timelines automatically generated based on these templates to qualitatively demonstrate the performance. The results confirm that our approach can effectively extract extensible templates from real-world timeline infographics.

Node-link diagrams are widely used to facilitate network explorations. However, when using a graph drawing technique to visualize networks, users often need to tune different algorithm-specific parameters iteratively by comparing the corresponding drawing results in order to achieve a desired visual effect. This trial and error process is often tedious and time-consuming, especially for non-expert users. Inspired by the powerful data modelling and prediction capabilities of deep learning techniques, we explore the possibility of applying deep learning techniques to graph drawing. Specifically, we propose using a graph-LSTM-based approach to directly map network structures to graph drawings. Given a set of layout examples as the training dataset, we train the proposed graph-LSTM-based model to capture their layout characteristics. Then, the trained model is used to generate graph drawings in a similar style for new networks. We evaluated the proposed approach on two special types of layouts (i.e., grid layouts and star layouts) and two general types of layouts (i.e., ForceAtlas2 and PivotMDS) in both qualitative and quantitative ways. The results provide support for the effectiveness of our approach. We also conducted a time cost assessment on the drawings of small graphs with 20 to 50 nodes. We further report the lessons we learned and discuss the limitations and future work.

A comprehensive and comprehensible summary of existing deep neural networks (DNNs) helps practitioners understand the behaviour and evolution of DNNs, offers insights for architecture optimization, and sheds light on the working mechanisms of DNNs. However, this summary is hard to obtain because of the complexity and diversity of DNN architectures. To address this issue, we develop DNN Genealogy, an interactive visualization tool, to offer a visual summary of representative DNNs and their evolutionary relationships. DNN Genealogy enables users to learn DNNs from multiple aspects, including architecture, performance, and evolutionary relationships. Central to this tool is a systematic analysis and visualization of 66 representative DNNs based on our analysis of 140 papers. A directed acyclic graph is used to illustrate the evolutionary relationships among these DNNs and highlight the representative DNNs. A focus + context visualization is developed to orient users during their exploration. A set of network glyphs is used in the graph to facilitate the understanding and comparing of DNNs in the context of the evolution. Case studies demonstrate that DNN Genealogy provides helpful guidance in understanding, applying, and optimizing DNNs. DNN Genealogy is extensible and will continue to be updated to reflect future advances in DNNs.

To relieve the pain of manually selecting machine learning algorithms and tuning hyperparameters, automated machine learning (AutoML) methods have been developed to automatically search for good models. Due to the huge model search space, it is impossible to try all models. Users tend to distrust automatic results and increase the search budget as much as they can, thereby undermining the efficiency of AutoML. To address these issues, we design and implement ATMSeer, an interactive visualization tool that supports users in refining the search space of AutoML and in analyzing the results. To guide the design of ATMSeer, we derive a workflow of using AutoML based on interviews with machine learning experts. A multi-granularity visualization is proposed to enable users to monitor the AutoML process, analyze the searched models, and refine the search space in real time. We demonstrate the utility and usability of ATMSeer through two case studies, expert interviews, and a user study with 13 end users.

Visual designs can be complex in modern data visualization systems, which poses special challenges for explaining them to the non-experts. However, few if any presentation tools are tailored for this purpose. In this study, we present Narvis, a slideshow authoring tool designed for introducing data visualizations to non-experts. Narvis targets two types of end users: teachers, experts in data visualization who produce tutorials for explaining a data visualization, and students, non-experts who try to understand visualization designs through tutorials. We present an analysis of requirements through close discussions with the two types of end users. The resulting considerations guide the design and implementation of Narvis. Additionally, to help teachers better organize their introduction slideshows, we specify a data visualization as a hierarchical combination of components, which are automatically detected and extracted by Narvis. The teachers craft an introduction slideshow through first organizing these components, and then explaining them sequentially. A series of templates are provided for adding annotations and animations to improve efficiency during the authoring process. We evaluate Narvis through a qualitative analysis of the authoring experience, and a preliminary evaluation of the generated slideshows.