ProtoSteer: Steering Deep Sequence Model with Prototypes

• Published in: IEEE transactions on visualization and computer graphics Vol. 26; no. 1; pp. 238 - 248
• Main Authors: Ming, Yao, Xu, Panpan, Cheng, Furui, Qu, Huamin, Ren, Liu
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Computational modeling; Computer Graphics; Data mining; Data models; Data visualization; Deep Learning; Experts; Explainable Artificial Intelligence (XAI); Humans; Machine learning; Models, Theoretical; Natural language processing; Predictive models; Problem solving; Prototype Learning; Prototypes; Recurrent Neural Networks (RNNs); Sequence Data; Steering; Subject specialists; Task analysis; User-Computer Interface
• ISSN: 1077-2626; 1941-0506; 1941-0506
• DOI: 10.1109/TVCG.2019.2934267

Recently we have witnessed growing adoption of deep sequence models (e.g. LSTMs) in many application domains, including predictive health care, natural language processing, and log analysis. However, the intricate working mechanism of these models confines their accessibility to the domain experts. Their black-box nature also makes it a challenging task to incorporate domain-specific knowledge of the experts into the model. In ProtoSteer (Prototype Steering), we tackle the challenge of directly involving the domain experts to steer a deep sequence model without relying on model developers as intermediaries. Our approach originates in case-based reasoning, which imitates the common human problem-solving process of consulting past experiences to solve new problems. We utilize ProSeNet (Prototype Sequence Network), which learns a small set of exemplar cases (i.e., prototypes) from historical data. In ProtoSteer they serve both as an efficient visual summary of the original data and explanations of model decisions. With ProtoSteer the domain experts can inspect, critique, and revise the prototypes interactively. The system then incorporates user-specified prototypes and incrementally updates the model. We conduct extensive case studies and expert interviews in application domains including sentiment analysis on texts and predictive diagnostics based on vehicle fault logs. The results demonstrate that involvements of domain users can help obtain more interpretable models with concise prototypes while retaining similar accuracy.