Preventing Failures Due to Dataset Shift: Learning Predictive Models That Transport

By Adarsh Subbaswamy, Peter F. Schulam, Suchi Saria. 2018

163 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

In Safety, Robustness & Interpretability

Citations in the corpus

Toward Causal Representation Learning (2021, background): “It also led to a range of follow-up work [32], [78], [97], [114], [115], [152], [153], [156], [167], [195], [204], [243], [263], [267], [277], [278], [281], complementing the studies of Bareinboim and Pearl [14], [185], and it inspired a thread of work in the statistics community exploiting…”
Learning explanations that are hard to vary (2020, background): “Other works connecting causality and learning through invariances are (Subbaswamy et al., 2019; Heinze-Deml and Meinshausen, 2017), and perhaps – most related to our work – (Arjovsky et al.”
Causality for Machine Learning (2019, background): “The line of work provided rather fruitful (Zhang et al., 2013; Weichwald et al., 2014; Zhang et al., 2015; Gong et al., 2016; Huang et al., 2017; Blöbaum et al., 2016; Guo et al., 2018; Wang et al., 2019; Subbaswamy et al., 2018; Rabanser et al., 2018; Li et al., 2018a; Lipton et al., 2018; Li et al”
Fairness Violations and Mitigation under Covariate Shift (2019, methodology): “When causal structure of the domains is known, recent work on causal domain adaptation [38, 61, 66, 68] identify predictors with stable accuracy under unseen changes in distribution.”
Deep Structural Causal Models for Tractable Counterfactual Inference (2020, background): “By explicitly modelling causal relationships and acknowledging the difference between causation and correlation, causality becomes a natural ﬁeld of study for improving the transparency, fairness, and robustness of DL-based systems [17, 18].”
Algorithm fairness in artificial intelligence for medicine and healthcare (2023, background): “…shifts, some guidelines have emphasized the importance of guaranteeing model stability to how the data were generated 118 , and the use of reactive or proactive approaches for intervening on temporal dataset shifts in early-warning systems such as those for the prediction of sepsis 117,184 .”
Causality matters in medical imaging (2019, background): “Interestingly, the same formalism of causal reasoning explored here was also shown to be especially well-suited for expressing and addressing issues of unfairness (e.g. social biases) 62 and dataset shift 63 in other contexts.”
Clinical artificial intelligence quality improvement: towards continual monitoring and updating of AI algorithms in healthcare (2022, background): “Model developers can also incorporate known sources of common-cause variation into the model to improve its generalizability 28,29 .”
Feature Robustness in Non-stationary Health Records: Caveats to Deployable Model Performance in Common Clinical Machine Learning Tasks (2019, background): “Another approach estimates a relationship between source and target domains that incorporates prior knowledge of how the data generating process might differ (or stay the same) between domains (Subbaswamy et al., 2019).”
Causal inference and counterfactual prediction in machine learning for actionable healthcare (2020, background): “A transport-able model can be integrated into clinical guidelines to augment healthcare with action-savvy predictions, in pursuit of better precision medicine.”
The Risks of Invariant Risk Minimization (2020, background): “Various works on invariant prediction (Muandet et al., 2013; Ghassami et al., 2017; Heinze-Deml et al., 2018; Rojas-Carulla et al., 2018; Subbaswamy et al., 2019; Christiansen et al., 2020) consider regression in both the linear and non-linear setting, but they exclusively focus on learning with…”