Model LineUpper: Supporting Interactive Model Comparison at Multiple Levels for AutoML

Narkar, S.; Zhang, Yunfeng; Liao, Q. Vera; Wang, Dakuo; Weisz, Justin D.

doi:10.1145/3397481.3450658

Cited by 21 publications

(12 citation statements)

References 25 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One recent research thread, Interactive Machine Learning [21], is a promising solution to the "black box" issue of AI systems. Interactive machine learning often relies on advanced visualization and interaction techniques (e.g., [18,51,86]), allowing users to monitor, interpret, and intervene the machine learning process so that they can establish trust toward the algorithm outputs. In a similar vein, a group of Google researchers recently built an experimental visualization system to help physicians understand the AI interpretations of breast cancer imaging data [10].…”

Section: Issues In the Implementation Of Ai-cdssmentioning

confidence: 99%

“Brilliant AI Doctor” in Rural Clinics: Challenges in AI-Powered Clinical Decision Support System Deployment

Wang¹,

Wang

Zhang

et al. 2021

Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems

Self Cite

111

View full text Add to dashboard Cite

Artificial intelligence (AI) technology has been increasingly used in the implementation of advanced Clinical Decision Support Systems (CDSS). Research demonstrated the potential usefulness of AI-powered CDSS (AI-CDSS) in clinical decision making scenarios. However, post-adoption user perception and experience remain understudied, especially in developing countries. Through observations and interviews with 22 clinicians from 6 rural clinics in China, this paper reports the various tensions between the design of an AI-CDSS system ("Brilliant Doctor") and the rural clinical context, such as the misalignment with local context and workflow, the technical limitations and usability barriers, as well as issues related to transparency and trustworthiness of AI-CDSS. Despite these tensions, all participants expressed positive attitudes toward the future of AI-CDSS, especially acting as "a doctor's AI assistant" to realize a Human-AI Collaboration future in clinical settings. Finally we draw on our findings to discuss implications for designing AI-CDSS interventions for rural clinical contexts in developing countries. CCS CONCEPTS• Human-centered computing → Collaborative and social computing.

show abstract

Section: Issues In the Implementation Of Ai-cdssmentioning

confidence: 99%

“Brilliant AI Doctor” in Rural Clinics: Challenges in AI-Powered Clinical Decision Support System Deployment

Wang¹,

Wang

Zhang

et al. 2021

Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems

Self Cite

111

View full text Add to dashboard Cite

show abstract

“…We can find support for this context-dependency in recent HCI works studying different XAI systems. For example, model debugging tools often integrate detailed local and global explanations (Narkar et al 2021;Hohman et al 2019). Decision-makers were found to have less desire for global explanations during time-constrained decisions, and prefer less distracting information (Xie et al 2020).…”

Section: Xai Evaluationmentioning

confidence: 99%

Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI

Liao

Zhang

Luss³

et al. 2022

HCOMP

View full text Add to dashboard Cite

Recent years have seen a surge of interest in the field of explainable AI (XAI), with a plethora of algorithms proposed in the literature. However, a lack of consensus on how to evaluate XAI hinders the advancement of the field. We highlight that XAI is not a monolithic set of technologies---researchers and practitioners have begun to leverage XAI algorithms to build XAI systems that serve different usage contexts, such as model debugging and decision-support. Algorithmic research of XAI, however, often does not account for these diverse downstream usage contexts, resulting in limited effectiveness or even unintended consequences for actual users, as well as difficulties for practitioners to make technical choices. We argue that one way to close the gap is to develop evaluation methods that account for different user requirements in these usage contexts. Towards this goal, we introduce a perspective of contextualized XAI evaluation by considering the relative importance of XAI evaluation criteria for prototypical usage contexts of XAI. To explore the context dependency of XAI evaluation criteria, we conduct two survey studies, one with XAI topical experts and another with crowd workers. Our results urge for responsible AI research with usage-informed evaluation practices, and provide a nuanced understanding of user requirements for XAI in different usage contexts.

show abstract

“…explainability, debugging user-interfaces, etc.) are used [35], or could be used [20], and how to design them [4,52]. We build a design probe 2 in the shape of a user-interface by performing literature studies, a formative study, and co-creation sessions consisting of 18 interviews, to explore uses of explainability for debugging.…”

Section: Introductionmentioning

confidence: 99%

How can Explainability Methods be Used to Support Bug Identification in Computer Vision Models?

Balayn

Rikalo

Lofi

et al. 2022

CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Deep learning models for image classifcation sufer from dangerous issues often discovered after deployment. The process of identifying bugs that cause these issues remains limited and understudied. Especially, explainability methods are often presented as obvious tools for bug identifcation. Yet, the current practice lacks an understanding of what kind of explanations can best support the diferent steps of the bug identifcation process, and how practitioners could interact with those explanations. Through a formative study and an iterative co-creation process, we build an interactive design probe providing various potentially relevant explainability functionalities, integrated into interfaces that allow for fexible workfows. Using the probe, we perform 18 user-studies with a diverse set of machine learning practitioners. Two-thirds of the practitioners engage in successful bug identifcation. They use multiple types of explanations, e.g. visual and textual ones, through non-standardized sequences of interactions including queries and exploration. Our results highlight the need for interactive, guiding, interfaces with diverse explanations, shedding light on future research directions. CCS CONCEPTS• Human-centered computing → User interface programming; Empirical studies in HCI ; • Computing methodologies → Computer vision; • Software and its engineering → Software testing and debugging.

show abstract

Model LineUpper: Supporting Interactive Model Comparison at Multiple Levels for AutoML

Cited by 21 publications

References 25 publications

“Brilliant AI Doctor” in Rural Clinics: Challenges in AI-Powered Clinical Decision Support System Deployment

“Brilliant AI Doctor” in Rural Clinics: Challenges in AI-Powered Clinical Decision Support System Deployment

Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI

How can Explainability Methods be Used to Support Bug Identification in Computer Vision Models?

Contact Info

Product

Resources

About