Interpreting Classifiers through Attribute Interactions in Datasets

07/24/2017
by   Andreas Henelius, et al.
0

In this work we present the novel ASTRID method for investigating which attribute interactions classifiers exploit when making predictions. Attribute interactions in classification tasks mean that two or more attributes together provide stronger evidence for a particular class label. Knowledge of such interactions makes models more interpretable by revealing associations between attributes. This has applications, e.g., in pharmacovigilance to identify interactions between drugs or in bioinformatics to investigate associations between single nucleotide polymorphisms. We also show how the found attribute partitioning is related to a factorisation of the data generating distribution and empirically demonstrate the utility of the proposed method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/22/2016

Finding Statistically Significant Attribute Interactions

In many data exploration tasks it is meaningful to identify groups of at...
research
10/15/2016

Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning

Collecting training images for all visual categories is not only expensi...
research
04/28/2023

Dissecting Recall of Factual Associations in Auto-Regressive Language Models

Transformer-based language models (LMs) are known to capture factual kno...
research
09/28/2020

A new network-base high-level data classification methodology (Quipus) by modeling attribute-attribute interactions

High-level classification algorithms focus on the interactions between i...
research
03/25/2021

Interpretable Approximation of High-Dimensional Data

In this paper we apply the previously introduced approximation method ba...
research
09/14/2020

New complex network building methodology for High Level Classification based on attribute-attribute interaction

High-level classification algorithms focus on the interactions between i...
research
03/29/2023

Three-way causal attribute partial order structure analysis

As an emerging concept cognitive learning model, partial order formal st...

Please sign up or login with your details

Forgot password? Click here to reset