Are Logistic Models Really Interpretable?
The demand for open and trustworthy AI models points towards widespread publishing of model weights. Consumers of these model weights must be able to act accordingly with the information provided. That said, one of the simplest AI classification models, Logistic Regression (LR), has an unwieldy interpretation of its model weights, with greater difficulties when extending LR to generalised additive models. In this work, we show via a User Study that skilled participants are unable to reliably reproduce the action of small LR models given the trained parameters. As an antidote to this, we define Linearised Additive Models (LAMs), an optimal piecewise linear approximation that augments any trained additive model equipped with a sigmoid link function, requiring no retraining. We argue that LAMs are more interpretable than logistic models -- survey participants are shown to solve model reasoning tasks with LAMs much more accurately than with LR given the same information. Furthermore, we show that LAMs do not suffer from large performance penalties in terms of ROC-AUC and calibration with respect to their logistic counterparts on a broad suite of public financial modelling data.
Code (0)
등록된 구현이 없습니다.
Tasks
Additive modelsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Interpretable Predictive Models for Healthcare via Rational Logistic Regression
The healthcare sector has experienced a rapid accumulation of digital data recently, especially in the form of electronic health records (EHRs). EHRs constitute a precious resource that IS researchers could utilize for c…
Deep LearningInductive BiasregressionA combined approach to the analysis of speech conversations in a contact center domain
The ever more accurate search for deep analysis in customer data is a really strong technological trend nowadays, quite appealing to both private and public companies. This is particularly true in the contact center doma…
Speech-to-TextSemi-supervised Logistic Learning Based on Exponential Tilt Mixture Models
Consider semi-supervised learning for classification, where both labeled and unlabeled data are available for training. The goal is to exploit both datasets to achieve higher prediction accuracy than just using labeled d…
General ClassificationregressionInterpretable Clinical Classification with Kolmogorov-Arnold Networks
The increasing use of machine learning in clinical decision support has been limited by the lack of transparency of many high-performing models. In clinical settings, predictions must be interpretable, auditable, and act…
Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics
Recent work incorporates pre-trained word embeddings such as BERT embeddings into Neural Topic Models (NTMs), generating highly coherent topics. However, with high-quality contextualized document representations, do we r…
ClusteringSentenceSentence EmbeddingsTopic Models+1