Counterfactual Invariance to Spurious Correlations
Dec 6, 2021
Speakers
Victor Veitch
Speaker · 1 follower
Alexander D'Amour
Speaker · 1 follower
Steve Yadlowsky
Speaker · 2 followers
Jacob Eisenstein
Speaker · 0 followers
About
Informally, a 'spurious correlation' is the dependence of a model on some aspect of the input data that an analyst thinks shouldn't matter. In machine learning, these have a know-it-when-you-see-it character; e.g., changing the gender of a sentence's subject changes a sentiment predictor's output. In this paper, we study counterfactual invariance, a causal formalization of the perturbative stress testing requirement that changing irrelevant parts of the input shouldn’t change model predictions. We connect counterfactual invariance to out-of-domain model performance, and provide practical schemes for learning (approximately) counterfactual invariant predictors (without access to counterfactual examples). It turns out that both the means and meaning of counterfactual invariance depend fundamentally on the true underlying causal structure of the data. Distinct causal structures require distinct regularization schemes to induce counterfactual invariance. Similarly, counterfactual invariance implies different domain shift guarantees depending on the underlying causal structure. This theory is supported by empirical results on text classification.Informally, a 'spurious correlation' is the dependence of a model on some aspect of the input data that an analyst thinks shouldn't matter. In machine learning, these have a know-it-when-you-see-it character; e.g., changing the gender of a sentence's subject changes a sentiment predictor's output. In this paper, we study counterfactual invariance, a causal formalization of the perturbative stress testing requirement that changing irrelevant parts of the input shouldn’t change model predictions.…
Organizer
NeurIPS 2021
Account · 1.9k followers
Categories
AI & Data Science
Category · 10.8k presentations
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Machine Learning for Smart Buildings: Applications and Perspectives
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Hyperparameter Tuning is All You Need for LISTA
Watch later
Xiaohan Chen, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Detecting Abandoned Oil Wells Using Machine Learning and Semantic Segmentation
Watch later
Michelle Lin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
New Frontiers in Federated Learning: Privacy, Fairness, Robustness, Personalization and Data Ownership - Opening Remarks
Watch later
Nghia Hoang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Speaker Introduction (Andreas)
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Adaptive Fine-tuning for Vision and Language Pre-trained Models
Watch later
Shentong Mo, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%