FRI-Feature Relevance Intervals for Interpretable and Interactive Data Exploration

Pfannschmidt, Lukas; Göpfert, Christina; Neumann, Ursula; Heider, Dominik; Hammer, Barbara

doi:10.1109/cibcb.2019.8791489

Cited by 3 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One can see that the complexity can limit the application of the method to small to medium-sized problems. This is in line with other all relevant feature selection methods [37] which exhibit much higher runtimes than simple sparse methods. While slightly bigger sets with, e.g.…”

Section: Equivalence Of Minrel(i) and Minrel * (I)supporting

confidence: 88%

See 1 more Smart Citation

Feature relevance determination for ordinal regression in the context of feature redundancies and privileged information

et al. 2020

Self Cite

View full text Add to dashboard Cite

Advances in machine learning technologies have led to increasingly powerful models in particular in the context of big data. Yet, many application scenarios demand for robustly interpretable models rather than optimum model accuracy; as an example, this is the case if potential biomarkers or causal factors should be discovered based on a set of given measurements. In this contribution, we focus on feature selection paradigms, which enable us to uncover relevant factors of a given regularity based on a sparse model. We focus on the important specific setting of linear ordinal regression, i.e. data have to be ranked into one of a finite number of ordered categories by a linear projection. Unlike previous work, we consider the case that features are potentially redundant, such that no unique minimum set of relevant features exists. We aim for an identification of all strongly and all weakly relevant features as well as their type of relevance (strong or weak); we achieve this goal by determining feature relevance bounds, which correspond to the minimum and maximum feature relevance, respectively, if searched over all equivalent models. In addition, we discuss how this setting enables us to substitute some of the features, e.g. due to their semantics, and how to extend the framework of feature relevance intervals to the setting of privileged information, i.e. potentially relevant information is available for training purposes only, but cannot be used for the prediction itself.

show abstract

Section: Equivalence Of Minrel(i) and Minrel * (I)supporting

confidence: 88%

“…Because the dz + c LPs are a significant factor, we proposed to solve them in parallel [37] which we evaluate in Appendix B.1.…”

Section: Time Complexitymentioning

confidence: 99%

Feature relevance determination for ordinal regression in the context of feature redundancies and privileged information

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, Auffarth et al [ 28 ] write that “redundancy measures how similar features are”. Chakraborty et al [ 29 ] and Pfannschmidt et al [ 30 , 31 ] argue that features or variables include redundancy if not all relevant features are required for a target application, that is, there exists no unique minimum feature set to solve a given task. This kind of redundancy, based on similarity of information, is in this work hereafter referred to as Redundancy Type II.…”

Section: Redundancy In Related Workmentioning

confidence: 99%

A Redundancy Metric Set within Possibility Theory for Multi-Sensor Systems

Holst

Lohweg

2021

Sensors

View full text Add to dashboard Cite

In intelligent technical multi-sensor systems, information is often at least partly redundant—either by design or inherently due to the dynamic processes of the observed system. If sensors are known to be redundant, (i) information processing can be engineered to be more robust against sensor failures, (ii) failures themselves can be detected more easily, and (iii) computational costs can be reduced. This contribution proposes a metric which quantifies the degree of redundancy between sensors. It is set within the possibility theory. Information coming from sensors in technical and cyber–physical systems are often imprecise, incomplete, biased, or affected by noise. Relations between information of sensors are often only spurious. In short, sensors are not fully reliable. The proposed metric adopts the ability of possibility theory to model incompleteness and imprecision exceptionally well. The focus is on avoiding the detection of spurious redundancy. This article defines redundancy in the context of possibilistic information, specifies requirements towards a redundancy metric, details the information processing, and evaluates the metric qualitatively on information coming from three technical datasets.

show abstract

“…(I) pre-model interpretability, which involves data exploration techniques such as PCA, k-means clustering (Alpaydin, 2020) and t-ditributed Stochastic Neighbor Embedding (tSNE) (Maaten and Hinton, 2008); (II) post-model interpretability, in which model-agnostic techniques are applied on blackbox models to analyze them locally, such as Local interpretable model-agnostic explanations (LIME) (Arrieta et al, 2020), DeepView (Schulz et al, 2020), Feature Relevance Information (FRI) (Pfannschmidt et al, 2019) and SHapley Additive ex-PLanations (SHAP)(Lundberg and Lee, 2017) just to name a few;…”

Section: Introductionmentioning

confidence: 99%

Interpretable Models Capable of Handling Systematic Missingness in Imbalanced Classes and Heterogeneous Datasets

Ghosh¹,

Baranowski²,

Biehl³

et al. 2022

Preprint

View full text Add to dashboard Cite

Application of interpretable machine learning techniques on medical datasets facilitate early and fast diagnoses, along with getting deeper insight into the data. Furthermore, the transparency of these models increase trust among application domain experts. Medical datasets face common issues such as heterogeneous measurements, imbalanced classes with limited sample size, and missing data, which hinder the straightforward application of machine learning techniques. In this paper we present a family of prototype-based (PB) interpretable models which are capable of handling these issues. The models introduced in this contribution show comparable or superior performance to alternative techniques applicable in such situations. However, unlike ensemble based models, which have to compromise on easy interpretation, the PB models here do not. Moreover we propose a strategy of harnessing the power of ensembles while maintaining the intrinsic interpretability of the

show abstract

FRI-Feature Relevance Intervals for Interpretable and Interactive Data Exploration

Cited by 3 publications

References 33 publications

Feature relevance determination for ordinal regression in the context of feature redundancies and privileged information

Feature relevance determination for ordinal regression in the context of feature redundancies and privileged information

A Redundancy Metric Set within Possibility Theory for Multi-Sensor Systems

Interpretable Models Capable of Handling Systematic Missingness in Imbalanced Classes and Heterogeneous Datasets

Contact Info

Product

Resources

About