Explainable Data Decompositions

Dalleiger, Sebastian; Vreeken, Jilles

doi:10.1609/aaai.v34i04.5780

Cited by 7 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, the regularizer tilts the optimization to prefer shorter patterns. To further push the weights to a binary solution we employ a W-shaped regularizer (Bai, Wang, and Liberty 2019;Dalleiger and Vreeken 2022), defined as…”

Section: Forward Passmentioning

confidence: 99%

Finding Interpretable Class-Specific Patterns through Efficient Neural Search

Walter,

Fischer,

Vreeken

2024

AAAI

View full text Add to dashboard Cite

Discovering patterns in data that best describe the differences between classes allows to hypothesize and reason about class-specific mechanisms. In molecular biology, for example, these bear the promise of advancing the understanding of cellular processes differing between tissues or diseases, which could lead to novel treatments. To be useful in practice, methods that tackle the problem of finding such differential patterns have to be readily interpretable by domain experts, and scalable to the extremely high-dimensional data. In this work, we propose a novel, inherently interpretable binary neural network architecture Diffnaps that extracts differential patterns from data. Diffnaps is scalable to hundreds of thousands of features and robust to noise, thus overcoming the limitations of current state-of-the-art methods in large-scale applications such as in biology. We show on synthetic and real world data, including three biological applications, that unlike its competitors, Diffnaps consistently yields accurate, succinct, and interpretable class descriptions.

show abstract

Section: Forward Passmentioning

confidence: 99%

Finding Interpretable Class-Specific Patterns through Efficient Neural Search

Walter,

Fischer,

Vreeken

2024

AAAI

View full text Add to dashboard Cite

show abstract

“…correlation [309], likelihood comparison [58] or evaluating how adding explanations to the model would improve prediction performance [253]. Le et al [144] also introduced a metric called "influence" which combines fidelity with information gain and compactness.…”

Section: Compactnessmentioning

confidence: 99%

From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI

Nauta¹,

Trienes²,

Pathak³

et al. 2022

Preprint

View full text Add to dashboard Cite

The rising popularity of explainable artificial intelligence (XAI) to understand high-performing black boxes, also raised the question of how to evaluate explanations of machine learning (ML) models. While interpretability and explainability are often presented as a subjectively validated binary property, we consider it a multi-faceted concept. We identify 12 conceptual properties, such as Compactness and Correctness, that should be evaluated for comprehensively assessing the quality of an explanation. Our so-called Co-12 properties serve as categorization scheme for systematically reviewing the evaluation practice of more than 300 papers published in the last 7 years at major AI and ML conferences that introduce an XAI method. We find that 1 in 3 papers evaluate exclusively with anecdotal evidence, and 1 in 5 papers evaluate with users. We also contribute to the call for objective, quantifiable evaluation methods by presenting an extensive overview of quantitative XAI evaluation methods. This systematic collection of evaluation methods provides researchers and practitioners with concrete tools to thoroughly validate, benchmark and compare new and existing XAI methods. This also opens up opportunities to include quantitative metrics as optimization criteria during model training in order to optimize for accuracy and interpretability simultaneously.

show abstract

Explainable AI: To Reveal the Logic of Black-Box Models

Chinu

Bansal²

2023

New Gener. Comput.

View full text Add to dashboard Cite

Explainable Data Decompositions

Cited by 7 publications

References 20 publications

Finding Interpretable Class-Specific Patterns through Efficient Neural Search

Finding Interpretable Class-Specific Patterns through Efficient Neural Search

From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI

Explainable AI: To Reveal the Logic of Black-Box Models

Contact Info

Product

Resources

About