The Rashomon Importance Distribution: Getting RID of Unstable, Single Model-based Variable Importance

• URL: http://arxiv.org/abs/2309.13775v4
• Date: Mon, 1 Apr 2024 22:59:31 GMT
• Title: The Rashomon Importance Distribution: Getting RID of Unstable, Single Model-based Variable Importance
• Authors: Jon Donnelly, Srikar Katta, Cynthia Rudin, Edward P. Browne,
• Abstract summary: Quantifying variable importance is essential for answering high-stakes questions in fields like genetics, public policy, and medicine. We propose a new variable importance framework that quantifies the importance of a variable across the set of all good models and is stable across the data distribution. Our framework is extremely flexible and can be integrated with most existing model classes and global variable importance metrics.
• Score: 16.641794438414745
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantifying variable importance is essential for answering high-stakes questions in fields like genetics, public policy, and medicine. Current methods generally calculate variable importance for a given model trained on a given dataset. However, for a given dataset, there may be many models that explain the target outcome equally well; without accounting for all possible explanations, different researchers may arrive at many conflicting yet equally valid conclusions given the same data. Additionally, even when accounting for all possible explanations for a given dataset, these insights may not generalize because not all good explanations are stable across reasonable data perturbations. We propose a new variable importance framework that quantifies the importance of a variable across the set of all good models and is stable across the data distribution. Our framework is extremely flexible and can be integrated with most existing model classes and global variable importance metrics. We demonstrate through experiments that our framework recovers variable importance rankings for complex simulation setups where other methods fail. Further, we show that our framework accurately estimates the true importance of a variable for the underlying data distribution. We provide theoretical guarantees on the consistency and finite sample error rates for our estimator. Finally, we demonstrate its utility with a real-world case study exploring which genes are important for predicting HIV load in persons with HIV, highlighting an important gene that has not previously been studied in connection with HIV. Code is available at https://github.com/jdonnelly36/Rashomon_Importance_Distribution.

Related papers

• On the Universal Truthfulness Hyperplane Inside LLMs [27.007142483859162]
  We investigate whether a universal truthfulness hyperplane that distinguishes the model's factually correct and incorrect outputs exists within the model. Our results indicate that increasing the diversity of the training datasets significantly enhances the performance in all scenarios.
  arXiv  Detail & Related papers  (2024-07-11T15:07:26Z)
• Semi-Supervised Learning for Deep Causal Generative Models [2.5847188023177403]
  We develop a semi-supervised deep causal generative model that exploits the causal relationships between variables to maximise the use of all available data. We leverage techniques from causal inference to infer missing values and subsequently generate realistic counterfactuals.
  arXiv  Detail & Related papers  (2024-03-27T16:06:37Z)
• Nonparametric Identifiability of Causal Representations from Unknown Interventions [63.1354734978244]
  We study causal representation learning, the task of inferring latent causal variables and their causal relations from mixtures of the variables. Our goal is to identify both the ground truth latents and their causal graph up to a set of ambiguities which we show to be irresolvable from interventional data.
  arXiv  Detail & Related papers  (2023-06-01T10:51:58Z)
• Leveraging sparse and shared feature activations for disentangled representation learning [112.22699167017471]
  We propose to leverage knowledge extracted from a diversified set of supervised tasks to learn a common disentangled representation. We validate our approach on six real world distribution shift benchmarks, and different data modalities.
  arXiv  Detail & Related papers  (2023-04-17T01:33:24Z)
• On the Strong Correlation Between Model Invariance and Generalization [54.812786542023325]
  Generalization captures a model's ability to classify unseen data. Invariance measures consistency of model predictions on transformations of the data. From a dataset-centric view, we find a certain model's accuracy and invariance linearly correlated on different test sets.
  arXiv  Detail & Related papers  (2022-07-14T17:08:25Z)
• Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets [53.34152466646884]
  In this paper, we show how bringing recent results on equivariant representation learning instantiated on structured spaces together with simple use of classical results on causal inference provides an effective practical solution. We demonstrate how our model allows dealing with more than one nuisance variable under some assumptions and can enable analysis of pooled scientific datasets in scenarios that would otherwise entail removing a large portion of the samples.
  arXiv  Detail & Related papers  (2022-03-29T04:54:06Z)
• Bayesian data combination model with Gaussian process latent variable model for mixed observed variables under NMAR missingness [0.0]
  It is difficult to obtain a "(quasi) single-source dataset" in which the variables of interest are simultaneously observed. It is necessary to utilize these datasets as a single-source dataset with missing variables. We propose a data fusion method that does not assume that datasets are homogenous.
  arXiv  Detail & Related papers  (2021-09-01T16:09:55Z)
• BayesIMP: Uncertainty Quantification for Causal Data Fusion [52.184885680729224]
  We study the causal data fusion problem, where datasets pertaining to multiple causal graphs are combined to estimate the average treatment effect of a target variable. We introduce a framework which combines ideas from probabilistic integration and kernel mean embeddings to represent interventional distributions in the reproducing kernel Hilbert space.
  arXiv  Detail & Related papers  (2021-06-07T10:14:18Z)
• OR-Net: Pointwise Relational Inference for Data Completion under Partial Observation [51.083573770706636]
  This work uses relational inference to fill in the incomplete data. We propose Omni-Relational Network (OR-Net) to model the pointwise relativity in two aspects.
  arXiv  Detail & Related papers  (2021-05-02T06:05:54Z)
• Evaluating Model Robustness and Stability to Dataset Shift [7.369475193451259]
  We propose a framework for analyzing stability of machine learning models. We use the original evaluation data to determine distributions under which the algorithm performs poorly. We estimate the algorithm's performance on the "worst-case" distribution.
  arXiv  Detail & Related papers  (2020-10-28T17:35:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.