A thesis compiling six papers that use causal invariance to improve graph neural networks' out-of-distribution generalization, interpretability, and robustness.
Distributionally Robust Losses for Latent Covariate Mixtures
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
While modern large-scale datasets often consist of heterogeneous subpopulations -- for example, multiple demographic groups or multiple text corpora -- the standard practice of minimizing average loss fails to guarantee uniformly low losses across all subpopulations. We propose a convex procedure that controls the worst-case performance over all subpopulations of a given size. Our procedure comes with finite-sample (nonparametric) convergence guarantees on the worst-off subpopulation. Empirically, we observe on lexical similarity, wine quality, and recidivism prediction tasks that our worst-case procedure learns models that do well against unseen subpopulations.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Causality for Modern Machine Learning
A thesis compiling six papers that use causal invariance to improve graph neural networks' out-of-distribution generalization, interpretability, and robustness.