arXiv subjects

Daniel A. Keim

Publications and source records attributed to Daniel A. Keim.

54 records · Page 3Linked to original sources

arXiv2022

ViNNPruner: Visual Interactive Pruning for Deep Learning

Neural networks grow vastly in size to tackle more sophisticated tasks. In many cases, such large networks are not deployable on particular hardware and need to be reduced in size. Pruning techniques help to shrink deep neural networks to smaller sizes by only decreasing their performance as little as possible. However, such pruning algorithms are often hard to understand by applying them and do not include domain knowledge which can potentially be bad for user goals. We propose ViNNPruner, a visual interactive pruning application that implements state-of-the-art pruning algorithms and the option for users to do manual pruning based on their knowledge. We show how the application facilitates gaining insights into automatic pruning algorithms and semi-automatically pruning oversized networks to make them more efficient using interactive visualizations.

cs.LG↗

arXiv2022

Promoting Ethical Awareness in Communication Analysis: Investigating Potentials and Limits of Visual Analytics for Intelligence Applications

Digital systems for analyzing human communication data have become prevalent in recent years. Intelligence analysis of communications data in investigative journalism, criminal intelligence, and law present particularly interesting cases, as they must take into account the often highly sensitive properties of the underlying operations and data. At the same time, these are areas where increasingly automated, sophisticated approaches systems can be particularly relevant, especially in terms of Big Data manageability. However, by the shifting of responsibilities, this also poses dangers. In addition to privacy concerns, these dangers relate to uncertain or poor data quality, leading to discrimination and potentially misleading insights. Visual analytics combines machine learning methods with interactive visual interfaces to enable human sense- and decision-making. This technique can be key for designing and operating meaningful interactive communication analysis systems that consider these ethical challenges. In this interdisciplinary work, a joint endeavor of computer scientists, ethicists, and scholars in Science & Technology Studies, we investigate and evaluate opportunities and risks involved in using Visual analytics approaches for communication analysis in intelligence applications in particular. We introduce, at first, the common technological systems used in communication analysis, further discussing the domain-specific ethical implications, tensions, and risks involved. We then make the case of how tailored Visual Analytics approaches may reduce and mitigate the described problems, both theoretically and through practical examples. We show that finding Visual Analytics design solutions for ethical issues is not a mere optimization task, but balancing out and negotiating these trade-offs has, as we argue, to be an integral aspect of the system design process from the outset.

cs.HC↗

arXiv2022

Characterizing Grounded Theory Approaches in Visualization

Grounded theory (GT) is a research methodology that entails a systematic workflow for theory generation grounded on emergent data. In this paper, we juxtapose GT workflows with typical workflows in visualization and visual analytics, shortly VIS, and underline the characteristics shared by these workflows. We explore the research landscape of VIS to observe where GT has been applied to generate VIS theories, explicitly as well as implicitly. We propose a "why" typology for characterizing aspects in VIS where GT can potentially play a significant role. We outline a "how" methodology for conducting GT research in VIS, which addresses the need for theoretical advancement in VIS while benefitting from other methods and techniques in VIS. We exemplify this "how" methodology by adopting GT approaches in studying the messages posted on VisGuides - an Open Discourse Forum for discussing visualization guidelines.

cs.HC↗

arXiv2022

Towards a Survey of Visualization Methods for Power Grids

With the ongoing emergence of smart and distributed grids, it becomes increasingly important to understand as well as improve legacy infrastructure while operating a much more interconnected and fragile architecture. To support this endeavor, a detailed simulation and real-life analysis are required. Leveraging advanced visualization and analytics methods can significantly improve and simplify tasks such as network analysis, maintenance, and planning, while also enabling operators to spot critical issues which are hard to detect otherwise. In this work, we work towards a comprehensive overview of the methods developed for the interactive visualization of power grids. We give an overview of the development of the field before motivating a range of comparison criteria and then evaluating the advantages and disadvantages of the single approaches. Finally, we derive a set of open research questions and possible further improvements to the field.

cs.HC↗

arXiv2022

CorpusVis: Visual Analysis of Digital Sheet Music Collections

Manually investigating sheet music collections is challenging for music analysts due to the magnitude and complexity of underlying features, structures, and contextual information. However, applying sophisticated algorithmic methods would require advanced technical expertise that analysts do not necessarily have. Bridging this gap, we contribute CorpusVis, an interactive visual workspace, enabling scalable and multi-faceted analysis. Our proposed visual analytics dashboard provides access to computational methods, generating varying perspectives on the same data. The proposed application uses metadata including composers, type, epoch, and low-level features, such as pitch, melody, and rhythm. To evaluate our approach, we conducted a pair analytics study with nine participants. The qualitative results show that CorpusVis supports users in performing exploratory and confirmatory analysis, leading them to new insights and findings. In addition, based on three exemplary workflows, we demonstrate how to apply our approach to different tasks, such as exploring musical features or comparing composers.

cs.HC↗

arXiv2021

Time Series Model Attribution Visualizations as Explanations

Attributions are a common local explanation technique for deep learning models on single samples as they are easily extractable and demonstrate the relevance of input values. In many cases, heatmaps visualize such attributions for samples, for instance, on images. However, heatmaps are not always the ideal visualization to explain certain model decisions for other data types. In this review, we focus on attribution visualizations for time series. We collect attribution heatmap visualizations and some alternatives, discuss the advantages as well as disadvantages and give a short position towards future opportunities for attributions and explanations for time series.

cs.LG↗

arXiv2021

TS-MULE: Local Interpretable Model-Agnostic Explanations for Time Series Forecast Models

Time series forecasting is a demanding task ranging from weather to failure forecasting with black-box models achieving state-of-the-art performances. However, understanding and debugging are not guaranteed. We propose TS-MULE, a local surrogate model explanation method specialized for time series extending the LIME approach. Our extended LIME works with various ways to segment and perturb the time series data. In our extension, we present six sampling segmentation approaches for time series to improve the quality of surrogate attributions and demonstrate their performances on three deep learning model architectures and three common multivariate time series datasets.

cs.LG↗

arXiv2021

Towards a Survey on Static and Dynamic Hypergraph Visualizations

Leveraging hypergraph structures to model advanced processes has gained much attention over the last few years in many areas, ranging from protein-interaction in computational biology to image retrieval using machine learning. Hypergraph models can provide a more accurate representation of the underlying processes while reducing the overall number of links compared to regular representations. However, interactive visualization methods for hypergraphs and hypergraph-based models have rarely been explored or systematically analyzed. This paper reviews the existing research landscape for hypergraph and hypergraph model visualizations and assesses the currently employed techniques. We provide an overview and a categorization of proposed approaches, focusing on performance, scalability, interaction support, successful evaluation, and the ability to represent different underlying data structures, including a recent demand for a temporal representation of interaction networks and their improvements beyond graph-based methods. Lastly, we discuss the strengths and weaknesses of the approaches and give an insight into the future challenges arising in this emerging research field.

cs.HC↗

arXiv2021

CommAID: Visual Analytics for Communication Analysis through Interactive Dynamics Modeling

Communication consists of both meta-information as well as content. Currently, the automated analysis of such data often focuses either on the network aspects via social network analysis or on the content, utilizing methods from text-mining. However, the first category of approaches does not leverage the rich content information, while the latter ignores the conversation environment and the temporal evolution, as evident in the meta-information. In contradiction to communication research, which stresses the importance of a holistic approach, both aspects are rarely applied simultaneously, and consequently, their combination has not yet received enough attention in automated analysis systems. In this work, we aim to address this challenge by discussing the difficulties and design decisions of such a path as well as contribute CommAID, a blueprint for a holistic strategy to communication analysis. It features an integrated visual analytics design to analyze communication networks through dynamics modeling, semantic pattern retrieval, and a user-adaptable and problem-specific machine learning-based retrieval system. An interactive multi-level matrix-based visualization facilitates a focused analysis of both network and content using inline visuals supporting cross-checks and reducing context switches. We evaluate our approach in both a case study and through formative evaluation with eight law enforcement experts using a real-world communication corpus. Results show that our solution surpasses existing techniques in terms of integration level and applicability. With this contribution, we aim to pave the path for a more holistic approach to communication analysis.

cs.HC↗

arXiv2021

Video-based Analysis of Soccer Matches

With the increasingly detailed investigation of game play and tactics in invasive team sports such as soccer, it becomes ever more important to present causes, actions and findings in a meaningful manner. Visualizations, especially when augmenting relevant information directly inside a video recording of a match, can significantly improve and simplify soccer match preparation and tactic planning. However, while many visualization techniques for soccer have been developed in recent years, few have been directly applied to the video-based analysis of soccer matches. This paper provides a comprehensive overview and categorization of the methods developed for the video-based visual analysis of soccer matches. While identifying the advantages and disadvantages of the individual approaches, we identify and discuss open research questions, soon enabling analysts to develop winning strategies more efficiently, do rapid failure analysis or identify weaknesses in opposing teams.

cs.CV↗

arXiv2021

Visual Analytics of Conversational Dynamics

Large-scale interaction networks of human communication are often modeled as complex graph structures, obscuring temporal patterns within individual conversations. To facilitate the understanding of such conversational dynamics, episodes with low or high communication activity as well as breaks in communication need to be detected to enable the identification of temporal interaction patterns. Traditional episode detection approaches are highly dependent on the choice of parameters, such as window-size or binning-resolution. In this paper, we present a novel technique for the identification of relevant episodes in bi-directional interaction sequences from abstract communication networks. We model communication as a continuous density function, allowing for a more robust segmentation into individual episodes and estimation of communication volume. Additionally, we define a tailored feature set to characterize conversational dynamics and enable a user-steered classification of communication behavior. We apply our technique to a real-world corpus of email data from a large European research institution. The results show that our technique allows users to effectively define, identify, and analyze relevant communication episodes.

cs.SI↗

arXiv2020

An Empirical Study of Explainable AI Techniques on Deep Learning Models For Time Series Tasks

Decision explanations of machine learning black-box models are often generated by applying Explainable AI (XAI) techniques. However, many proposed XAI methods produce unverified outputs. Evaluation and verification are usually achieved with a visual interpretation by humans on individual images or text. In this preregistration, we propose an empirical study and benchmark framework to apply attribution methods for neural networks developed for images and text data on time series. We present a methodology to automatically evaluate and rank attribution techniques on time series using perturbation methods to identify reliable approaches.

cs.LG↗

arXiv2020

Visual Analytics for Temporal Hypergraph Model Exploration

Many processes, from gene interaction in biology to computer networks to social media, can be modeled more precisely as temporal hypergraphs than by regular graphs. This is because hypergraphs generalize graphs by extending edges to connect any number of vertices, allowing complex relationships to be described more accurately and predict their behavior over time. However, the interactive exploration and seamless refinement of such hypergraph-based prediction models still pose a major challenge. We contribute Hyper-Matrix, a novel visual analytics technique that addresses this challenge through a tight coupling between machine-learning and interactive visualizations. In particular, the technique incorporates a geometric deep learning model as a blueprint for problem-specific models while integrating visualizations for graph-based and category-based data with a novel combination of interactions for an effective user-driven exploration of hypergraph models. To eliminate demanding context switches and ensure scalability, our matrix-based visualization provides drill-down capabilities across multiple levels of semantic zoom, from an overview of model predictions down to the content. We facilitate a focused analysis of relevant connections and groups based on interactive user-steering for filtering and search tasks, a dynamically modifiable partition hierarchy, various matrix reordering techniques, and interactive model feedback. We evaluate our technique in a case study and through formative evaluation with law enforcement experts using real-world internet forum communication data. The results show that our approach surpasses existing solutions in terms of scalability and applicability, enables the incorporation of domain knowledge, and allows for fast search-space traversal. With the technique, we pave the way for the visual analytics of temporal hypergraphs in a wide variety of domains.

cs.HC↗

arXiv2020

MultiSegVA: Using Visual Analytics to Segment Biologging Time Series on Multiple Scales

Segmenting biologging time series of animals on multiple temporal scales is an essential step that requires complex techniques with careful parameterization and possibly cross-domain expertise. Yet, there is a lack of visual-interactive tools that strongly support such multi-scale segmentation. To close this gap, we present our MultiSegVA platform for interactively defining segmentation techniques and parameters on multiple temporal scales. MultiSegVA primarily contributes tailored, visual-interactive means and visual analytics paradigms for segmenting unlabeled time series on multiple scales. Further, to flexibly compose the multi-scale segmentation, the platform contributes a new visual query language that links a variety of segmentation techniques. To illustrate our approach, we present a domain-oriented set of segmentation techniques derived in collaboration with movement ecologists. We demonstrate the applicability and usefulness of MultiSegVA in two real-world use cases from movement ecology, related to behavior analysis after environment-aware segmentation, and after progressive clustering. Expert feedback from movement ecologists shows the effectiveness of tailored visual-interactive means and visual analytics paradigms at segmenting multi-scale data, enabling them to perform semantically meaningful analyses. A third use case demonstrates that MultiSegVA is generalizable to other domains.

cs.HC↗

arXiv2020

Slope-Dependent Rendering of Parallel Coordinates to Reduce Density Distortion and Ghost Clusters

Parallel coordinates are a popular technique to visualize multi-dimensional data. However, they face a significant problem influencing the perception and interpretation of patterns. The distance between two parallel lines differs based on their slope. Vertical lines are rendered longer and closer to each other than horizontal lines. This problem is inherent in the technique and has two main consequences: (1) clusters which have a steep slope between two axes are visually more prominent than horizontal clusters. (2) Noise and clutter can be perceived as clusters, as a few parallel vertical lines visually emerge as a ghost cluster. Our paper makes two contributions: First, we formalize the problem and show its impact. Second, we present a novel technique to reduce the effects by rendering the polylines of the parallel coordinates based on their slope: horizontal lines are rendered with the default width, lines with a steep slope with a thinner line. Our technique avoids density distortions of clusters, can be computed in linear time, and can be added on top of most parallel coordinate variations. To demonstrate the usefulness, we show examples and compare them to the classical rendering.

cs.GR↗

arXiv2020

SpatialRugs: Enhancing Spatial Awareness of Movement in Dense Pixel Visualizations

Compact visual summaries of spatio-temporal movement data often strive to express accurate positions of movers. We present SpatialRugs, a technique to enhance the spatial awareness of movements in dense pixel visualizations. SpatialRugs apply 2D colormaps to visualize location mapped to a juxtaposed display. We explore the effect of various colormaps discussing perceptual limitations and introduce a custom color-smoothing method to mitigate distorted patterns of collective movement behavior.

cs.HC↗

arXiv2019

Towards a Rigorous Evaluation of XAI Methods on Time Series

Explainable Artificial Intelligence (XAI) methods are typically deployed to explain and debug black-box machine learning models. However, most proposed XAI methods are black-boxes themselves and designed for images. Thus, they rely on visual interpretability to evaluate and prove explanations. In this work, we apply XAI methods previously used in the image and text-domain on time series. We present a methodology to test and evaluate various XAI methods on time series by introducing new verification techniques to incorporate the temporal dimension. We further conduct preliminary experiments to assess the quality of selected XAI method explanations with various verification methods on a range of datasets and inspecting quality metrics on it. We demonstrate that in our initial experiments, SHAP works robust for all models, but others like DeepLIFT, LRP, and Saliency Maps work better with specific architectures.

cs.LG↗

arXiv2019

Progressive Data Science: Potential and Challenges

Data science requires time-consuming iterative manual activities. In particular, activities such as data selection, preprocessing, transformation, and mining, highly depend on iterative trial-and-error processes that could be sped-up significantly by providing quick feedback on the impact of changes. The idea of progressive data science is to compute the results of changes in a progressive manner, returning a first approximation of results quickly and allow iterative refinements until converging to a final result. Enabling the user to interact with the intermediate results allows an early detection of erroneous or suboptimal choices, the guided definition of modifications to the pipeline and their quick assessment. In this paper, we discuss the progressiveness challenges arising in different steps of the data science pipeline. We describe how changes in each step of the pipeline impact the subsequent steps and outline why progressive data science will help to make the process more effective. Computing progressive approximations of outcomes resulting from changes creates numerous research challenges, especially if the changes are made in the early steps of the pipeline. We discuss these challenges and outline first steps towards progressiveness, which, we argue, will ultimately help to significantly speed-up the overall data science process.

cs.HC↗