Domino: Discovering Systematic Errors with Cross-Modal Embeddings

Abstract

Machine learning models that achieve high overall accuracy often make systematic errors on important subsets (or slices) of data. Identifying underperforming slices is particularly challenging when working with high-dimensional inputs (e.g. images, audio), where important slices are often unlabeled. In order to address this issue, recent studies have proposed automated slice discovery methods (SDMs), which leverage learned model representations to mine input data for slices on which a model performs poorly. To be useful to a practitioner, these methods must identify slices that are both underperforming and coherent (i.e. united by a human-understandable concept). However, no quantitative evaluation framework currently exists for rigorously assessing SDMs with respect to these criteria. Additionally, prior qualitative evaluations have shown that SDMs often identify slices that are incoherent. In this work, we address these challenges by first designing a principled evaluation framework that enables a quantitative comparison of SDMs across 1,235 slice discovery settings in three input domains (natural images, medical images, and time-series data). Then, motivated by the recent development of powerful cross-modal representation learning approaches, we present Domino, an SDM that leverages cross-modal embeddings and a novel error-aware mixture model to discover and describe coherent slices. We find that Domino accurately identifies 36% of the 1,235 slices in our framework - a 12 percentage point improvement over prior methods. Further, Domino is the first SDM that can provide natural language descriptions of identified slices, correctly generating the exact name of the slice in 35% of settings.

arXiv commentICLR 2022 (Oral)

Cited by in corpus (8)

• Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning
• Assaying Out-Of-Distribution Generalization in Transfer Learning
• ScatterShot: Interactive In-context Example Curation for Text Transformation
• Better, Not Just More: Data-Centric Machine Learning for Earth Observation
• Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
• Slicing Through Bias: Explaining Performance Gaps in Medical Image Analysis using Slice Discovery Methods
• VLSlice: Interactive Vision-and-Language Slice Discovery
• Site-specific Deterministic Temperature and Humidity Forecasts with Explainable and Reliable Machine Learning