A Simple Framework for XAI Comparisons with a Case Study

Yeo, Guo Feng Anders; Hudson, Irene L.; Akman, David; Chan, Jeffrey

doi:10.1109/icaibd55127.2022.9820551

Cited by 1 publication

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Post-hoc methods perform an additional procedure after the model is established in order to provide insight to a prediction or model logic, well-known methods include Local Interpretable Model Agnostic Explanation (LIME) (Ribeiro et al 2016). Whilst verifying the evaluation of post-hoc methods can be done through external means and domain knowledge (Adadi & Berrada 2018), post-hoc methods, specifically post-hoc feature importance methods, have inconsistent and mixed efficacy representing either the models or dataset (Yeo et al 2022). On the other hand, the intrinsically interpretable instance selection purpose is two-fold in XAI, the instances themselves are a simpler representation of the dataset and the models based on a smaller subset tend to be simpler and therefore more interpretable.…”

Section: Introductionmentioning

confidence: 99%

Visualising instance selection for improved explainability using feature extraction

2023

MODSIM2023, 25th International Congress on Modelling and Simulation.

View full text Add to dashboard Cite

Advancement in the collection and storage of data, alongside the modern emphasis of automated decision making have lead to datasets growing exponentially in size and complexity over the last four decades. Lever-aging excessively large data through traditional machine learning can lead to exorbitant run times, storage and general computational bloat, with the trained model potentially being sub-optimal (Kohavi & John 1997). Dimensionality reduction through selection and extraction are common methods of mitigating these issues. Extraction methods map the existing data to lower dimensional space whilst attempting to maintain the characteristics of the original dataset, whilst selection methods attempt to take a representative subset of the data. Alongside elevating the technical computational bloat, data reduction provides a parsimonious representation of the dataset, resulting in comparably simpler models which are more intrinsically interpretable. Therefore, data reduction techniques are included within Explainable Artificial Intelligence (XAI) (Barredo Arrieta et al. 2020). With the increasing reliance on automated decision making, the number of publications related to XAI has increased rapidly over the last ten years. A machine learning model should be not only accurate, but also transparent with an interpretable logic for proposed predictions. Therefore, machine learning models are used for both predictive purposes and retrospective data exploration and analysis.

show abstract

Section: Introductionmentioning

confidence: 99%

Visualising instance selection for improved explainability using feature extraction

2023

MODSIM2023, 25th International Congress on Modelling and Simulation.

View full text Add to dashboard Cite

show abstract

A Simple Framework for XAI Comparisons with a Case Study

Cited by 1 publication

References 22 publications

Visualising instance selection for improved explainability using feature extraction

Visualising instance selection for improved explainability using feature extraction

Contact Info

Product

Resources

About