Relative Feature Importance

• URL: http://arxiv.org/abs/2007.08283v1
• Date: Thu, 16 Jul 2020 12:20:22 GMT
• Title: Relative Feature Importance
• Authors: Gunnar K\"onig, Christoph Molnar, Bernd Bischl, Moritz Grosse-Wentrup
• Abstract summary: Relative Feature Importance (RFI) is a generalization of Permutation Feature Importance (PFI) and Conditional Feature Importance (CFI) RFI allows for a more nuanced feature importance computation beyond the PFI versus CFI dichotomy. We derive general interpretation rules for RFI based on a detailed theoretical analysis of the implications of relative feature relevance.
• Score: 1.4474137122906163
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Interpretable Machine Learning (IML) methods are used to gain insight into the relevance of a feature of interest for the performance of a model. Commonly used IML methods differ in whether they consider features of interest in isolation, e.g., Permutation Feature Importance (PFI), or in relation to all remaining feature variables, e.g., Conditional Feature Importance (CFI). As such, the perturbation mechanisms inherent to PFI and CFI represent extreme reference points. We introduce Relative Feature Importance (RFI), a generalization of PFI and CFI that allows for a more nuanced feature importance computation beyond the PFI versus CFI dichotomy. With RFI, the importance of a feature relative to any other subset of features can be assessed, including variables that were not available at training time. We derive general interpretation rules for RFI based on a detailed theoretical analysis of the implications of relative feature relevance, and demonstrate the method's usefulness on simulated examples.

Related papers

• Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning [67.90033766878962]
  Self-supervised feature learning (RL) often rely on information-theoretic principles, termed mutual information skill learning (MISL)<n>Our work investigates MISL through the lens of identifiable representation learning.<n>We prove that Contrastive Successor Features (CSF) can provably recover the environment's ground-truth features up to a linear transformation.
  arXiv  Detail & Related papers  (2025-07-19T20:48:46Z)
• Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs [34.52554840674882]
  This paper argues that mechanistic interpretability should prioritize feature consistency in SAEs.<n>We propose using the Pairwise Dictionary Mean Correlation Coefficient as a practical metric to operationalize consistency.
  arXiv  Detail & Related papers  (2025-05-26T17:31:36Z)
• How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective [64.00022624183781]
  Large language models (LLMs) can assess relevance and support information retrieval (IR) tasks. We investigate how different LLM modules contribute to relevance judgment through the lens of mechanistic interpretability.
  arXiv  Detail & Related papers  (2025-04-10T16:14:55Z)
• Optimal ablation for interpretability [5.108909395876561]
  Interpretability studies often involve tracing the flow of information through machine learning models. Prior work quantifies the importance of a model component on a particular task by measuring the impact of performing ablation on that component, or simulating model inference with the component disabled. We propose a new method, optimal ablation (OA), and show that OA-based component importance has theoretical and empirical advantages over measuring importance via other ablation methods.
  arXiv  Detail & Related papers  (2024-09-16T02:45:54Z)
• 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)
• Regularized Multivariate Functional Principal Component Analysis [3.4238565157486187]
  This paper introduces a novel approach called regularized theCA (ReCA) to address the issue of controlling the roughness of Principal Components. The proposed method generates multivariate functional PCs, providing a concise and interpretable representation of the data.
  arXiv  Detail & Related papers  (2023-06-24T14:22:25Z)
• Opening the random forest black box by the analysis of the mutual impact of features [0.0]
  We propose two novel approaches that focus on the mutual impact of features in random forests. MFI and MIR are very promising to shed light on the complex relationships between features and outcome.
  arXiv  Detail & Related papers  (2023-04-05T15:03:46Z)
• 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)
• Transforming Feature Space to Interpret Machine Learning Models [91.62936410696409]
  This contribution proposes a novel approach that interprets machine-learning models through the lens of feature space transformations. It can be used to enhance unconditional as well as conditional post-hoc diagnostic tools. A case study on remote-sensing landcover classification with 46 features is used to demonstrate the potential of the proposed approach.
  arXiv  Detail & Related papers  (2021-04-09T10:48:11Z)
• 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)
• The role of feature space in atomistic learning [62.997667081978825]
  Physically-inspired descriptors play a key role in the application of machine-learning techniques to atomistic simulations. We introduce a framework to compare different sets of descriptors, and different ways of transforming them by means of metrics and kernels. We compare representations built in terms of n-body correlations of the atom density, quantitatively assessing the information loss associated with the use of low-order features.
  arXiv  Detail & Related papers  (2020-09-06T14:12:09Z)
• Estimating Structural Target Functions using Machine Learning and Influence Functions [103.47897241856603]
  We propose a new framework for statistical machine learning of target functions arising as identifiable functionals from statistical models. This framework is problem- and model-agnostic and can be used to estimate a broad variety of target parameters of interest in applied statistics. We put particular focus on so-called coarsening at random/doubly robust problems with partially unobserved information.
  arXiv  Detail & Related papers  (2020-08-14T16:48:29Z)
• Out-of-distribution Generalization via Partial Feature Decorrelation [72.96261704851683]
  We present a novel Partial Feature Decorrelation Learning (PFDL) algorithm, which jointly optimize a feature decomposition network and the target image classification model. The experiments on real-world datasets demonstrate that our method can improve the backbone model's accuracy on OOD image classification datasets.
  arXiv  Detail & Related papers  (2020-07-30T05:48:48Z)
• Controlling for sparsity in sparse factor analysis models: adaptive latent feature sharing for piecewise linear dimensionality reduction [2.896192909215469]
  We propose a simple and tractable parametric feature allocation model which can address key limitations of current latent feature decomposition techniques. We derive a novel adaptive Factor analysis (aFA), as well as, an adaptive probabilistic principle component analysis (aPPCA) capable of flexible structure discovery and dimensionality reduction. We show that aPPCA and aFA can infer interpretable high level features both when applied on raw MNIST and when applied for interpreting autoencoder features.
  arXiv  Detail & Related papers  (2020-06-22T16:09:11Z)

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.