Model Sketching: Centering Concepts in Early-Stage Machine Learning Model Design

要旨

Machine learning practitioners often end up tunneling on low-level technical details like model architectures and performance metrics. Could early model development instead focus on high-level questions of which factors a model ought to pay attention to? Inspired by the practice of sketching in design, which distills ideas to their minimal representation, we introduce model sketching: a technical framework for iteratively and rapidly authoring functional approximations of a machine learning model's decision-making logic. Model sketching refocuses practitioner attention on composing high-level, human-understandable concepts that the model is expected to reason over (e.g., profanity, racism, or sarcasm in a content moderation task) using zero-shot concept instantiation. In an evaluation with 17 ML practitioners, model sketching reframed thinking from implementation to higher-level exploration, prompted iteration on a broader range of model designs, and helped identify gaps in the problem formulation—all in a fraction of the time ordinarily required to build a model.

著者
Michelle S.. Lam
Stanford University, Stanford, California, United States
Zixian Ma
Stanford University, San Francisco, California, United States
Anne Li
Stanford University, Stanford, California, United States
Izequiel Freitas
Stanford University, Stanford, California, United States
Dakuo Wang
Northeastern University, Boston, Massachusetts, United States
James A.. Landay
Stanford University, Stanford, California, United States
Michael S.. Bernstein
Stanford University, Stanford, California, United States
論文URL

https://doi.org/10.1145/3544548.3581290

動画

会議: CHI 2023

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2023.acm.org/)

セッション: Tools for data scientists and Literature Reviews

Hall A
6 件の発表
2023-04-25 23:30:00
2023-04-26 00:55:00