The Berkelmans-Pries Feature Importance Method: A Generic Measure of
Informativeness of Features
- URL: http://arxiv.org/abs/2301.04740v1
- Date: Wed, 11 Jan 2023 22:18:19 GMT
- Title: The Berkelmans-Pries Feature Importance Method: A Generic Measure of
Informativeness of Features
- Authors: Joris Pries, Guus Berkelmans, Sandjai Bhulai, Rob van der Mei
- Abstract summary: We introduce a new global approach named the Berkelmans-Pries FI method, which is based on a combination of Shapley values and the Berkelmans-Pries dependency function.
We experimentally show for a large collection of FI methods (468) that existing methods do not have the same useful properties.
This shows that the Berkelmans-Pries FI method is a highly valuable tool for analyzing datasets with complex interdependencies.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Over the past few years, the use of machine learning models has emerged as a
generic and powerful means for prediction purposes. At the same time, there is
a growing demand for interpretability of prediction models. To determine which
features of a dataset are important to predict a target variable $Y$, a Feature
Importance (FI) method can be used. By quantifying how important each feature
is for predicting $Y$, irrelevant features can be identified and removed, which
could increase the speed and accuracy of a model, and moreover, important
features can be discovered, which could lead to valuable insights. A major
problem with evaluating FI methods, is that the ground truth FI is often
unknown. As a consequence, existing FI methods do not give the exact correct FI
values. This is one of the many reasons why it can be hard to properly
interpret the results of an FI method. Motivated by this, we introduce a new
global approach named the Berkelmans-Pries FI method, which is based on a
combination of Shapley values and the Berkelmans-Pries dependency function. We
prove that our method has many useful properties, and accurately predicts the
correct FI values for several cases where the ground truth FI can be derived in
an exact manner. We experimentally show for a large collection of FI methods
(468) that existing methods do not have the same useful properties. This shows
that the Berkelmans-Pries FI method is a highly valuable tool for analyzing
datasets with complex interdependencies.
Related papers
- 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) - Predicting is not Understanding: Recognizing and Addressing
Underspecification in Machine Learning [47.651130958272155]
Underspecification refers to the existence of multiple models that are indistinguishable in their in-domain accuracy.
We formalize the concept of underspecification and propose a method to identify and partially address it.
arXiv Detail & Related papers (2022-07-06T11:20:40Z) - "Will You Find These Shortcuts?" A Protocol for Evaluating the
Faithfulness of Input Salience Methods for Text Classification [38.22453895596424]
We present a protocol for faithfulness evaluation that makes use of partially synthetic data to obtain ground truth for feature importance ranking.
We do an in-depth analysis of four standard salience method classes on a range of datasets and shortcuts for BERT and LSTM models.
We recommend following the protocol for each new task and model combination to find the best method for identifying shortcuts.
arXiv Detail & Related papers (2021-11-14T15:31:29Z) - Direct Advantage Estimation [63.52264764099532]
We show that the expected return may depend on the policy in an undesirable way which could slow down learning.
We propose the Direct Advantage Estimation (DAE), a novel method that can model the advantage function and estimate it directly from data.
If desired, value functions can also be seamlessly integrated into DAE and be updated in a similar way to Temporal Difference Learning.
arXiv Detail & Related papers (2021-09-13T16:09:31Z) - Combining Feature and Instance Attribution to Detect Artifacts [62.63504976810927]
We propose methods to facilitate identification of training data artifacts.
We show that this proposed training-feature attribution approach can be used to uncover artifacts in training data.
We execute a small user study to evaluate whether these methods are useful to NLP researchers in practice.
arXiv Detail & Related papers (2021-07-01T09:26:13Z) - Search Methods for Sufficient, Socially-Aligned Feature Importance
Explanations with In-Distribution Counterfactuals [72.00815192668193]
Feature importance (FI) estimates are a popular form of explanation, and they are commonly created and evaluated by computing the change in model confidence caused by removing certain input features at test time.
We study several under-explored dimensions of FI-based explanations, providing conceptual and empirical improvements for this form of explanation.
arXiv Detail & Related papers (2021-06-01T20:36:48Z) - Do Feature Attribution Methods Correctly Attribute Features? [5.58592454173439]
Feature attribution methods are exceedingly popular in interpretable machine learning.
There is no consensus on the definition of "attribution"
We evaluate three methods: saliency maps, rationales, and attention.
arXiv Detail & Related papers (2021-04-27T20:35:30Z) - Interpretable Multi-dataset Evaluation for Named Entity Recognition [110.64368106131062]
We present a general methodology for interpretable evaluation for the named entity recognition (NER) task.
The proposed evaluation method enables us to interpret the differences in models and datasets, as well as the interplay between them.
By making our analysis tool available, we make it easy for future researchers to run similar analyses and drive progress in this area.
arXiv Detail & Related papers (2020-11-13T10:53:27Z) - 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) - 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.