Inference for Interpretable Machine Learning: Fast, Model-Agnostic Confidence Intervals for Feature Importance

• URL: http://arxiv.org/abs/2206.02088v1
• Date: Sun, 5 Jun 2022 03:14:48 GMT
• Title: Inference for Interpretable Machine Learning: Fast, Model-Agnostic Confidence Intervals for Feature Importance
• Authors: Luqin Gan, Lili Zheng, Genevera I. Allen
• Abstract summary: We develop confidence intervals for a widely-used form of machine learning interpretation: feature importance. We do so by leveraging a form of random observation and feature subsampling called minipatch ensembles. Our approach is fast as computations needed for inference come nearly for free as part of the ensemble learning process.
• Score: 1.2891210250935146
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In order to trust machine learning for high-stakes problems, we need models to be both reliable and interpretable. Recently, there has been a growing body of work on interpretable machine learning which generates human understandable insights into data, models, or predictions. At the same time, there has been increased interest in quantifying the reliability and uncertainty of machine learning predictions, often in the form of confidence intervals for predictions using conformal inference. Yet, there has been relatively little attention given to the reliability and uncertainty of machine learning interpretations, which is the focus of this paper. Our goal is to develop confidence intervals for a widely-used form of machine learning interpretation: feature importance. We specifically seek to develop universal model-agnostic and assumption-light confidence intervals for feature importance that will be valid for any machine learning model and for any regression or classification task. We do so by leveraging a form of random observation and feature subsampling called minipatch ensembles and show that our approach provides assumption-light asymptotic coverage for the feature importance score of any model. Further, our approach is fast as computations needed for inference come nearly for free as part of the ensemble learning process. Finally, we also show that our same procedure can be leveraged to provide valid confidence intervals for predictions, hence providing fast, simultaneous quantification of the uncertainty of both model predictions and interpretations. We validate our intervals on a series of synthetic and real data examples, showing that our approach detects the correct important features and exhibits many computational and statistical advantages over existing methods.

Related papers

• Reliable Probabilistic Human Trajectory Prediction for Autonomous Applications [1.8294777056635267]
  Vehicle systems need reliable, accurate, fast, resource-efficient, scalable, and low-latency trajectory predictions. This paper presents a lightweight method to address these requirements, combining Long Short-Term Memory and Mixture Density Networks. We discuss essential requirements for human trajectory prediction in autonomous vehicle applications and demonstrate our method's performance using traffic-related datasets.
  arXiv  Detail & Related papers  (2024-10-09T14:08:39Z)
• Improving Adaptive Conformal Prediction Using Self-Supervised Learning [72.2614468437919]
  We train an auxiliary model with a self-supervised pretext task on top of an existing predictive model and use the self-supervised error as an additional feature to estimate nonconformity scores. We empirically demonstrate the benefit of the additional information using both synthetic and real data on the efficiency (width), deficit, and excess of conformal prediction intervals.
  arXiv  Detail & Related papers  (2023-02-23T18:57:14Z)
• Prediction-Powered Inference [68.97619568620709]
  Prediction-powered inference is a framework for performing valid statistical inference when an experimental dataset is supplemented with predictions from a machine-learning system. The framework yields simple algorithms for computing provably valid confidence intervals for quantities such as means, quantiles, and linear and logistic regression coefficients. Prediction-powered inference could enable researchers to draw valid and more data-efficient conclusions using machine learning.
  arXiv  Detail & Related papers  (2023-01-23T18:59:28Z)
• Robustness of Machine Learning Models Beyond Adversarial Attacks [0.0]
  We show that the widely used concept of adversarial robustness and closely related metrics are not necessarily valid metrics for determining the robustness of ML models. We propose a flexible approach that models possible perturbations in input data individually for each application. This is then combined with a probabilistic approach that computes the likelihood that a real-world perturbation will change a prediction.
  arXiv  Detail & Related papers  (2022-04-21T12:09:49Z)
• Masked prediction tasks: a parameter identifiability view [49.533046139235466]
  We focus on the widely used self-supervised learning method of predicting masked tokens. We show that there is a rich landscape of possibilities, out of which some prediction tasks yield identifiability, while others do not.
  arXiv  Detail & Related papers  (2022-02-18T17:09:32Z)
• A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification [1.90365714903665]
  This hands-on introduction is aimed at a reader interested in the practical implementation of distribution-free UQ. We will include many explanatory illustrations, examples, and code samples in Python, with PyTorch syntax.
  arXiv  Detail & Related papers  (2021-07-15T17:59:50Z)
• Learning Accurate Dense Correspondences and When to Trust Them [161.76275845530964]
  We aim to estimate a dense flow field relating two images, coupled with a robust pixel-wise confidence map. We develop a flexible probabilistic approach that jointly learns the flow prediction and its uncertainty. Our approach obtains state-of-the-art results on challenging geometric matching and optical flow datasets.
  arXiv  Detail & Related papers  (2021-01-05T18:54:11Z)
• Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning [123.3472310767721]
  Prediction credibility measures are fundamental in statistics and machine learning. These measures should account for the wide variety of models used in practice. The framework developed in this work expresses the credibility as a risk-fit trade-off.
  arXiv  Detail & Related papers  (2020-11-24T19:52:38Z)
• Accurate and Robust Feature Importance Estimation under Distribution Shifts [49.58991359544005]
  PRoFILE is a novel feature importance estimation method. We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
  arXiv  Detail & Related papers  (2020-09-30T05:29:01Z)
• Towards a More Reliable Interpretation of Machine Learning Outputs for Safety-Critical Systems using Feature Importance Fusion [0.0]
  We introduce a novel fusion metric and compare it to the state-of-the-art. Our approach is tested on synthetic data, where the ground truth is known. Results show that our feature importance ensemble Framework overall produces 15% less feature importance error compared to existing methods.
  arXiv  Detail & Related papers  (2020-09-11T15:51:52Z)

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.