Interactive Visualization for Fostering Trust in ML
2023, Chau, Polo, Endert, Alex, Keim, Daniel A., Oelke, Daniela
The use of artificial intelligence continues to impact a broad variety of domains, application areas, and people. However, interpretability, understandability, responsibility, accountability, and fairness of the algorithms' results - all crucial for increasing humans' trust into the systems - are still largely missing. The purpose of this seminar is to understand how these components factor into the holistic view of trust. Further, this seminar seeks to identify design guidelines and best practices for how to build interactive visualization systems to calibrate trust.
Towards visual debugging for multi-target time series classification
2020, Schlegel, Udo, Cakmak, Eren, Arnout, Hiba, El-Assady, Mennatallah, Oelke, Daniela, Keim, Daniel A.
Multi-target classification of multivariate time series data poses a challenge in many real-world applications (e.g., predictive maintenance). Machine learning methods, such as random forests and neural networks, support training these classifiers. However, the debugging and analysis of possible misclassifications remain challenging due to the often complex relations between targets, classes, and the multivariate time series data. We propose a model-agnostic visual debugging workflow for multi-target time series classification that enables the examination of relations between targets, partially correct predictions, potential confusions, and the classified time series data. The workflow, as well as the prototype, aims to foster an in-depth analysis of multi-target classification results to identify potential causes of mispredictions visually. We demonstrate the usefulness of the workflow in the field of predictive maintenance in a usage scenario to show how users can iteratively explore and identify critical classes, as well as, relationships between targets.
Feature-Based Visual Exploration of Text Classification
2015, Stoffel, Florian, Flekova, Lucie, Oelke, Daniela, Gurevych, Iryna, Keim, Daniel A.
There are many applications of text classification such as gender attribution in market research or the identification of forged product reviews on e-commerce sites. Although several automatic methods provide satisfying performance in most application cases, we see a gap in supporting the analyst to understand the results and derive knowledge for future application scenarios. In this paper, we present a visualization driven application that allows analysts to gain insight in text classification tasks such as sentiment detection or authorship attribution on feature level, built with a practitioner’s way of reasoning in mind, the Text Classification Analysis Process.
Real-Time Visualization of Streaming Text Data : Tasks and Challenges
2011, Rohrdantz, Christian, Oelke, Daniela, Krstajic, Milos, Fischer, Fabian
Real-time visualization of text streams is crucial for different analysis scenarios and can be expected to become one of the important future research topics in the text visualization domain. Especially the complex requirements of real-time text analysis tasks lead to new visualization challenges, which will be structured and described in this paper. First, we give a definition of what we consider to be a text stream and emphasize the importance of different real-world application scenarios. Then, we summarize research challenges related to different parts of the analysis process and identify those challenges that are exclusive to real-time streaming text visualization. We review related work with respect to the question which of the challenges have been addressed in the past and what solutions have been suggested. Finally, we identify the open issues and potential future research subjects in this vibrant area.
The Role of Interactive Visualization in Fostering Trust in AI
2021, Beauxis-Aussalet, Emma, Behrisch, Michael, Borgo, Rita, Chau, Duen Horng, Collins, Christopher, El-Assady, Mennatallah, Keim, Daniel A., Oelke, Daniela, Schreck, Tobias, Strobelt, Hendrik
The increasing use of artificial intelligence (AI) technologies across application domains has prompted our society to pay closer attention to AI's trustworthiness, fairness, interpretability, and accountability. In order to foster trust in AI, it is important to consider the potential of interactive visualization, and how such visualizations help build trust in AI systems. This manifesto discusses the relevance of interactive visualizations and makes the following four claims: i) trust is not a technical problem, ii) trust is dynamic, iii) visualization cannot address all aspects of trust, and iv) visualization is crucial for human agency in AI.
Towards A Rigorous Evaluation Of XAI Methods On Time Series
2019-10, Schlegel, Udo, Arnout, Hiba, El-Assady, Mennatallah, Oelke, Daniela, Keim, Daniel A.
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.
Comparative Exploration of Document Collections : a Visual Analytics Approach
2014, Oelke, Daniela, Strobelt, Hendrik, Rohrdantz, Christian, Gurevych, Iryna, Deussen, Oliver
We present an analysis and visualization method for computing what distinguishes a given document collection from others. We determine topics that discriminate a subset of collections from the remaining ones by applying probabilistic topic modeling and subsequently approximating the two relevant criteria distinctiveness and characteristicness algorithmically through a set of heuristics. Furthermore, we suggest a novel visualization method called DiTop-View, in which topics are represented by glyphs (topic coins) that are arranged on a 2D plane. Topic coins are designed to encode all information necessary for performing comparative analyses such as the class membership of a topic, its most probable terms and the discriminative relations. We evaluate our topic analysis using statistical measures and a small user experiment and present an expert case study with researchers from political sciences analyzing two real-world datasets.
The Impact of Immersion on Cluster Identification Tasks
2020-01, Kraus, Matthias, Weiler, Niklas, Oelke, Daniela, Kehrer, Johannes, Keim, Daniel A., Fuchs, Johannes
Recent developments in technology encourage the use of head-mounted displays (HMDs) as a medium to explore visualizations in virtual realities (VRs). VR environments (VREs) enable new, more immersive visualization design spaces compared to traditional computer screens. Previous studies in different domains, such as medicine, psychology, and geology, report a positive effect of immersion, e.g., on learning performance or phobia treatment effectiveness. Our work presented in this paper assesses the applicability of those findings to a common task from the information visualization (InfoVis) domain. We conducted a quantitative user study to investigate the impact of immersion on cluster identification tasks in scatterplot visualizations. The main experiment was carried out with 18 participants in a within-subjects setting using four different visualizations, (1) a 2D scatterplot matrix on a screen, (2) a 3D scatterplot on a screen, (3) a 3D scatterplot miniature in a VRE and (4) a fully immersive 3D scatterplot in a VRE. The four visualization design spaces vary in their level of immersion, as shown in a supplementary study. The results of our main study indicate that task performance differs between the investigated visualization design spaces in terms of accuracy, efficiency, memorability, sense of orientation, and user preference. In particular, the 2D visualization on the screen performed worse compared to the 3D visualizations with regard to the measured variables. The study shows that an increased level of immersion can be a substantial benefit in the context of 3D data and cluster detection.
Lessons on Combining Topology and Geography : Visual Analytics for Electrical Outage Management
2016, Jäger, Alexander, Mittelstädt, Sebastian, Oelke, Daniela, Sander, Sonja, Platz, Axel, Bouwman, Gies, Keim, Daniel A.
Outage management in electrical networks is a complex task for operators and requires comprehensive overviews of the topology. At the same time valuable information for detecting the root cause may have geographical context such as digging activities or falling trees. Consequently, vendors of state-of-the-art SCADA systems started to integrate this valuable information source as well. However, in todays systems both views are separated, requiring operators to mentally connect the geographical and topological information. The wish of operators is to provide a comprehensive combination of both spaces in a single view. However, how to project geographical elements into the topology to support the workflow of real operators is yet unclear. In this paper, we present a design study for an interactive visualization system that provides a comprehensive overview for power grid operators. It provides full coverage of both spaces in order to measure how real operators make use of the geographical information. It bypasses the projection problem by interactive brushing-and-linking to support associative analysis. We extracted the mental-model of domain experts in real use cases and found a general bias source in sequential analysis of two spaces. We contribute our problem and task abstraction, lessons learned, and implications for future research.
Visual analysis of next-generation sequencing data to detect overlapping genes in bacterial genomes
2011-10, Simon, Svenja, Oelke, Daniela, Landstorfer, Richard, Neuhaus, Klaus, Keim, Daniel A.
Next generation sequencing (NGS) technologies are about to revolutionize biological research. Being able to sequence large amounts of DNA or, indirectly, RNA sequences in a short time period opens numerous new possibilities. However, analyzing the large amounts of data generated in NGS is a serious challenge, which requires novel data analysis and visualization methods to allow the biological experimenter to understand the results. In this paper, we describe a novel system to deal with the flood of data generated by transcriptome sequencing (RNA-seq) using NGS. Our system allows the analyzer to get a quick overview of the data and interactively explore interesting regions based on the three important parameters coverage, transcription, and fit. In particular, our system supports the NGS analysis in the following respects: (1) Representation of the coverage sequence in a way that no artifacts are introduced. (2) Easy determination of a fit of an open reading frame (ORF) to a transcript by mapping the coverage sequence directly into the ORF representation. (3) Providing automatic support for finding interesting regions to address the problems that the overwhelming volume of data comes with. (4) Providing an overview representation that allows parameter tuning and enables quick access to interesting areas of the genome. We show the usefulness of our system by a case study in the area of overlapping gene detection in a bacterial genome.