Towards a More Reliable Interpretation of Machine Learning Outputs for
Safety-Critical Systems using Feature Importance Fusion
- URL: http://arxiv.org/abs/2009.05501v1
- Date: Fri, 11 Sep 2020 15:51:52 GMT
- Title: Towards a More Reliable Interpretation of Machine Learning Outputs for
Safety-Critical Systems using Feature Importance Fusion
- Authors: Divish Rengasamy, Benjamin Rothwell, Grazziela Figueredo
- Abstract summary: 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.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: When machine learning supports decision-making in safety-critical systems, it
is important to verify and understand the reasons why a particular output is
produced. Although feature importance calculation approaches assist in
interpretation, there is a lack of consensus regarding how features' importance
is quantified, which makes the explanations offered for the outcomes mostly
unreliable. A possible solution to address the lack of agreement is to combine
the results from multiple feature importance quantifiers to reduce the variance
of estimates. Our hypothesis is that this will lead to more robust and
trustworthy interpretations of the contribution of each feature to machine
learning predictions. To assist test this hypothesis, we propose an extensible
Framework divided in four main parts: (i) traditional data pre-processing and
preparation for predictive machine learning models; (ii) predictive machine
learning; (iii) feature importance quantification and (iv) feature importance
decision fusion using an ensemble strategy. We also 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. We compare different fusion
approaches and their results for both training and test sets. We also
investigate how different characteristics within the datasets affect the
feature importance ensembles studied. Results show that our feature importance
ensemble Framework overall produces 15% less feature importance error compared
to existing methods. Additionally, results reveal that different levels of
noise in the datasets do not affect the feature importance ensembles' ability
to accurately quantify feature importance, whereas the feature importance
quantification error increases with the number of features and number of
orthogonal informative features.
Related papers
- Matched Machine Learning: A Generalized Framework for Treatment Effect
Inference With Learned Metrics [87.05961347040237]
We introduce Matched Machine Learning, a framework that combines the flexibility of machine learning black boxes with the interpretability of matching.
Our framework uses machine learning to learn an optimal metric for matching units and estimating outcomes.
We show empirically that instances of Matched Machine Learning perform on par with black-box machine learning methods and better than existing matching methods for similar problems.
arXiv Detail & Related papers (2023-04-03T19:32:30Z) - 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) - EFI: A Toolbox for Feature Importance Fusion and Interpretation in
Python [1.593222804814135]
Ensemble Feature Importance (EFI) is an open-source Python toolbox for machine learning (ML) researchers, domain experts, and decision makers.
EFI provides robust and accurate feature importance quantification and more reliable mechanistic interpretation of feature importance for prediction problems.
arXiv Detail & Related papers (2022-08-08T18:02:37Z) - Inherent Inconsistencies of Feature Importance [6.02357145653815]
Feature importance is a method that assigns scores to the contribution of individual features on prediction outcomes.
This paper presents an axiomatic framework designed to establish coherent relationships among the different contexts of feature importance scores.
arXiv Detail & Related papers (2022-06-16T14:21:51Z) - Sample-Efficient Reinforcement Learning in the Presence of Exogenous
Information [77.19830787312743]
In real-world reinforcement learning applications the learner's observation space is ubiquitously high-dimensional with both relevant and irrelevant information about the task at hand.
We introduce a new problem setting for reinforcement learning, the Exogenous Decision Process (ExoMDP), in which the state space admits an (unknown) factorization into a small controllable component and a large irrelevant component.
We provide a new algorithm, ExoRL, which learns a near-optimal policy with sample complexity in the size of the endogenous component.
arXiv Detail & Related papers (2022-06-09T05:19:32Z) - Inference for Interpretable Machine Learning: Fast, Model-Agnostic
Confidence Intervals for Feature Importance [1.2891210250935146]
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.
arXiv Detail & Related papers (2022-06-05T03:14:48Z) - Mechanistic Interpretation of Machine Learning Inference: A Fuzzy
Feature Importance Fusion Approach [0.39146761527401425]
There is a lack of consensus regarding how feature importance should be quantified.
Current state-of-the-art ensemble feature importance fusion uses crisp techniques to fuse results from different approaches.
Here we show how the use of fuzzy data fusion methods can overcome some of the important limitations of crisp fusion methods.
arXiv Detail & Related papers (2021-10-22T11:22:21Z) - Bayesian Importance of Features (BIF) [11.312036995195594]
We use the Dirichlet distribution to define the importance of input features and learn it via approximate Bayesian inference.
The learned importance has probabilistic interpretation and provides the relative significance of each input feature to a model's output.
We show the effectiveness of our method on a variety of synthetic and real datasets.
arXiv Detail & Related papers (2020-10-26T19:55:58Z) - Counterfactual Representation Learning with Balancing Weights [74.67296491574318]
Key to causal inference with observational data is achieving balance in predictive features associated with each treatment type.
Recent literature has explored representation learning to achieve this goal.
We develop an algorithm for flexible, scalable and accurate estimation of causal effects.
arXiv Detail & Related papers (2020-10-23T19:06:03Z) - 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) - Causal Feature Selection for Algorithmic Fairness [61.767399505764736]
We consider fairness in the integration component of data management.
We propose an approach to identify a sub-collection of features that ensure the fairness of the dataset.
arXiv Detail & Related papers (2020-06-10T20:20:10Z)
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.