当前位置: X-MOL 学术IEEE Trans. Vis. Comput. Graph. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
ProtoSteer: Steering Deep Sequence Model with Prototypes.
IEEE Transactions on Visualization and Computer Graphics ( IF 4.7 ) Pub Date : 2019-09-13 , DOI: 10.1109/tvcg.2019.2934267
Yao Ming , Panpan Xu , Furui Cheng , Huamin Qu , Liu Ren

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.

中文翻译:

ProtoSteer:指导原型的深度序列模型。

最近,我们目睹了深度序列模型(例如LSTM)在许多应用领域中的采用率不断提高,包括预测性医疗保健,自然语言处理和日志分析。但是,这些模型的复杂工作机制限制了它们对领域专家的可访问性。他们的黑盒性质也使得将专家的特定领域知识纳入模型中成为一项艰巨的任务。在ProtoSteer(原型指导)中,我们解决了直接让领域专家参与指导深层序列模型而又不依赖模型开发者作为中介的挑战。我们的方法源自基于案例的推理,它模仿了咨询过去经验以解决新问题的常见人类问题解决过程。我们利用ProSeNet(原型序列网络)它从历史数据中学习了少量的示例案例(即原型)。在ProtoSteer中,它们既可以作为原始数据的有效可视化摘要,也可以作为模型决策的解释。借助ProtoSteer,领域专家可以交互地检查,批判和修改原型。然后,系统合并用户指定的原型,并逐步更新模型。我们在应用领域进行广泛的案例研究和专家访谈,包括文本情感分析和基于车辆故障日志的预测诊断。结果表明,领域用户的参与可以帮助获得具有简洁原型的更多可解释模型,同时保持相似的准确性。在ProtoSteer中,它们既可以作为原始数据的有效可视化摘要,也可以作为模型决策的解释。借助ProtoSteer,领域专家可以交互地检查,批判和修改原型。然后,系统合并用户指定的原型,并逐步更新模型。我们在应用领域进行广泛的案例研究和专家访谈,包括文本情感分析和基于车辆故障日志的预测诊断。结果表明,领域用户的参与可以帮助获得具有简洁原型的更多可解释模型,同时保持相似的准确性。在ProtoSteer中,它们既可以作为原始数据的有效可视化摘要,也可以作为模型决策的解释。使用ProtoSteer,领域专家可以交互地检查,批判和修改原型。然后,系统合并用户指定的原型,并逐步更新模型。我们在应用领域进行广泛的案例研究和专家访谈,包括文本情感分析和基于车辆故障日志的预测诊断。结果表明,领域用户的参与可以帮助获得具有简洁原型的更多可解释模型,同时保持相似的准确性。然后,系统合并用户指定的原型,并逐步更新模型。我们在应用领域进行广泛的案例研究和专家访谈,包括文本情感分析和基于车辆故障日志的预测诊断。结果表明,领域用户的参与可以帮助获得具有简洁原型的更多可解释模型,同时保持相似的准确性。然后,系统合并用户指定的原型,并逐步更新模型。我们在应用领域进行广泛的案例研究和专家访谈,包括文本情感分析和基于车辆故障日志的预测诊断。结果表明,领域用户的参与可以帮助获得具有简洁原型的更多可解释模型,同时保持相似的准确性。
更新日期:2019-11-01
down
wechat
bug