Confident Feature Ranking
- URL: http://arxiv.org/abs/2307.15361v2
- Date: Thu, 18 Apr 2024 11:44:26 GMT
- Title: Confident Feature Ranking
- Authors: Bitya Neuhof, Yuval Benjamini,
- Abstract summary: We present a framework for quantifying the uncertainty in global importance values.
We propose a novel method for the post-hoc interpretation of feature importance values.
- Score: 2.0564549686015594
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Machine learning models are widely applied in various fields. Stakeholders often use post-hoc feature importance methods to better understand the input features' contribution to the models' predictions. The interpretation of the importance values provided by these methods is frequently based on the relative order of the features (their ranking) rather than the importance values themselves. Since the order may be unstable, we present a framework for quantifying the uncertainty in global importance values. We propose a novel method for the post-hoc interpretation of feature importance values that is based on the framework and pairwise comparisons of the feature importance values. This method produces simultaneous confidence intervals for the features' ranks, which include the ``true'' (infinite sample) ranks with high probability, and enables the selection of the set of the top-k important features.
Related papers
- Prospector Heads: Generalized Feature Attribution for Large Models & Data [82.02696069543454]
We introduce prospector heads, an efficient and interpretable alternative to explanation-based attribution methods.
We demonstrate how prospector heads enable improved interpretation and discovery of class-specific patterns in input data.
arXiv Detail & Related papers (2024-02-18T23:01:28Z) - Statistical Significance of Feature Importance Rankings [3.8642937395065124]
We devise techniques that ensure the most important features are correct with high-probability guarantees.
These assess the set of $K$ top-ranked features, as well as the order of its elements.
We then introduce two efficient sampling algorithms that identify the $K$ most important features, perhaps in order, with probability exceeding $1-alpha$.
arXiv Detail & Related papers (2024-01-28T23:14:51Z) - An Additive Instance-Wise Approach to Multi-class Model Interpretation [53.87578024052922]
Interpretable machine learning offers insights into what factors drive a certain prediction of a black-box system.
Existing methods mainly focus on selecting explanatory input features, which follow either locally additive or instance-wise approaches.
This work exploits the strengths of both methods and proposes a global framework for learning local explanations simultaneously for multiple target classes.
arXiv Detail & Related papers (2022-07-07T06:50:27Z) - 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) - An Efficient and Accurate Rough Set for Feature Selection,
Classification and Knowledge Representation [89.5951484413208]
This paper present a strong data mining method based on rough set, which can realize feature selection, classification and knowledge representation at the same time.
We first find the ineffectiveness of rough set because of overfitting, especially in processing noise attribute, and propose a robust measurement for an attribute, called relative importance.
Experimental results on public benchmark data sets show that the proposed framework achieves higher accurcy than seven popular or the state-of-the-art feature selection methods.
arXiv Detail & Related papers (2021-12-29T12:45:49Z) - 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) - Bayesian Attention Modules [65.52970388117923]
We propose a scalable version of attention that is easy to implement and optimize.
Our experiments show the proposed method brings consistent improvements over the corresponding baselines.
arXiv Detail & Related papers (2020-10-20T20:30:55Z) - 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) - A general framework for inference on algorithm-agnostic variable
importance [3.441021278275805]
We propose a framework for non inference on interpretable algorithm-agnostic variable importance.
We show that our proposal has good operating characteristics, and we illustrate it with data from a study of an antibody against HIV-1 infection.
arXiv Detail & Related papers (2020-04-07T20:09:21Z) - Value-driven Hindsight Modelling [68.658900923595]
Value estimation is a critical component of the reinforcement learning (RL) paradigm.
Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function.
We develop an approach for representation learning in RL that sits in between these two extremes.
This provides tractable prediction targets that are directly relevant for a task, and can thus accelerate learning the value function.
arXiv Detail & Related papers (2020-02-19T18:10:20Z)
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.