Underspecification Presents Challenges for Credibility in Modern Machine Learning

by   Alexander D'Amour, et al.

ML models often exhibit unexpectedly poor behavior when they are deployed in real-world domains. We identify underspecification as a key reason for these failures. An ML pipeline is underspecified when it can return many predictors with equivalently strong held-out performance in the training domain. Underspecification is common in modern ML pipelines, such as those based on deep learning. Predictors returned by underspecified pipelines are often treated as equivalent based on their training domain performance, but we show here that such predictors can behave very differently in deployment domains. This ambiguity can lead to instability and poor model behavior in practice, and is a distinct failure mode from previously identified issues arising from structural mismatch between training and deployment domains. We show that this problem appears in a wide variety of practical ML pipelines, using examples from computer vision, medical imaging, natural language processing, clinical risk prediction based on electronic health records, and medical genomics. Our results show the need to explicitly account for underspecification in modeling pipelines that are intended for real-world deployment in any domain.



page 15

page 16

page 21

page 26

page 30


Towards autonomic orchestration of machine learning pipelines in future networks

Machine learning (ML) techniques are being increasingly used in mobile n...

Picket: Self-supervised Data Diagnostics for ML Pipelines

Data corruption is an impediment to modern machine learning deployments....

A Real-World Demonstration of Machine Learning Generalizability: Intracranial Hemorrhage Detection on Head CT

Machine learning (ML) holds great promise in transforming healthcare. Wh...

Developing and Deploying Machine Learning Pipelines against Real-Time Image Streams from the PACS

Executing machine learning (ML) pipelines on radiology images is hard du...

Finding Label and Model Errors in Perception Data With Learned Observation Assertions

ML is being deployed in complex, real-world scenarios where errors have ...

Evolution of Scikit-Learn Pipelines with Dynamic Structured Grammatical Evolution

The deployment of Machine Learning (ML) models is a difficult and time-c...

Automatically Debugging AutoML Pipelines using Maro: ML Automated Remediation Oracle (Extended Version)

Machine learning in practice often involves complex pipelines for data c...

Code Repositories


Course "Practical Machine Learning", Week 4, Prediction Assignment Writeup

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.