A new approach to rationalization identifies true rationales by considering causal relationships.
problem Existing rationalization methods struggle with spuriousness, where snippets with similar contributions are hard to distinguish.
method The method leverages causal inference to identify non-spurious rationales, defining probabilities of causation based on a structural causal model.
result The proposed causal rationalization outperforms existing methods on real-world datasets.
The paper formalizes criteria for non-spurious and disentangled representations using causal methods.
problem Formalizing criteria for non-spurious and disentangled representations in representation learning.
method Causal perspective, counterfactual quantities, observable consequences of causal assertions.
result Computable metrics for assessing representation learning based on observed data.
A self-supervised debiasing method using rank regularization mitigates spurious correlations in neural networks.
problem Spurious correlations cause biases in deep neural networks, affecting generalization.
method Spectral analysis of latent representations, rank regularization, self-supervised pretraining, debiasing of downstream tasks.
result The proposed framework significantly improves generalization performance and outperforms supervised debiasing approaches.
Method trains a debiased model from a biased one by focusing on samples that contradict the bias.
problem Training neural networks can lead to biased predictions due to spurious correlations.
method Train a pair of neural networks, intentionally biasing one and debiasing the other by focusing on contradictory samples.
result Our method significantly improves training against various types of biases, sometimes outperforming explicit supervision methods.
Paper examines trade/no trade patterns in illiquid stocks, highlighting effects of varying zero returns probabilities.
problem Detecting long-run trade/no trade effects in illiquid stocks with varying zero returns probabilities.
method Proposes a framework considering constant and time-varying zero returns probabilities, analyzing trade/no trade categorical sequences.
result Long-run trade/no trade effects may be spuriously detected in presence of non-constant zero returns probabilities.
Deconfounds neural network representation similarity metrics to improve consistency and accuracy.
problem Confounding by population structure in similarity metrics like RSA and CKA.
method Covariate adjustment regression to adjust for confounders.
result Improves detection of semantically similar neural networks and consistency in transfer learning.
A neural framework corrects bias in estimating individual treatment effects.
problem Estimating individual treatment effects from observational data.
method An anchored neural architecture and precision-corrected intersection-bound inference.
result Corrected bias and maintained nominal coverage in high-dimensional settings.
LaCIM avoids spurious correlation by modeling latent causal factors.
problem Avoiding spurious correlation in supervised learning.
method Introducing latent variables for causal prediction and optimizing over latent space.
result Improved interpretability, robustness, and prediction power on OOD scenarios.
Study identifies failure modes of machine learning models in out-of-distribution settings.
problem Machine learning models fail to generalize well to new, unseen data.
method Theoretical study of gradient-descent-trained linear classifiers on easy-to-learn tasks, followed by experiments on modern neural networks.
result Two failure modes of spurious correlations are uncovered: geometric and statistical.
Recent sequential pattern mining methods have used the minimum description length (MDL) principle to define an encoding scheme which describes an algorithm for mining the most compressing patterns in a database. We present a novel subsequence interleaving model based on a probabilistic model of the sequence database, w…
New algorithm finds unbiased subnetworks in biased datasets.
problem Finding unbiased subnetworks in biased neural networks.
method Debiased Contrastive Weight Pruning (DCWP) algorithm.
result DCWP significantly outperforms state-of-the-art debiasing methods.
We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks sampled from the same distribution. The task identities of the unseen tasks are not provided. To perform well, the policy must infer the tas…
New method MRI improves machine learning models' ability to generalize to unseen data.
problem Machine learning models often fail to generalize well to out-of-distribution data.
method Introduces a new notion of invariance (MRI) and a practical version (MRI-v1) to improve model generalization.
result MRI-v1 guarantees invariant predictors and outperforms IRM-v1 in various settings.
Logit correction improves model performance by correcting spurious correlations.
problem Spurious correlations lead to poor model performance during inference.
method Proposes logit correction (LC) loss to mitigate spurious correlations.
result LC loss outperforms state-of-the-art solutions by 5.5% absolute improvement.
What do binary (or probabilistic) forecasting abilities have to do with overall performance? We map the difference between (univariate) binary predictions, bets and "beliefs" (expressed as a specific "event" will happen/will not happen) and real-world continuous payoffs (numerical benefits or harm from an event) and sh…
Sharp bounds on negative impact identified from observational data.
problem Identifying the fraction of users negatively affected by a treatment.
method Developed robust inference algorithm to derive tightest-possible bounds on negative impact.
result Valid conservative bounds on the fraction negatively affected, even when functions are mislearned.