RKHS-SHAP: Shapley values for kernel methods
Feature attribution for kernel methods is often heuristic and not individualised for each
prediction. To address this, we turn to the concept of Shapley values (SV), a coalition game …
prediction. To address this, we turn to the concept of Shapley values (SV), a coalition game …
Explaining the uncertain: Stochastic Shapley values for Gaussian process models
We present a novel approach for explaining Gaussian processes (GPs) that can utilize the
full analytical covariance structure present in GPs. Our method is based on the popular …
full analytical covariance structure present in GPs. Our method is based on the popular …
Feature interactions reveal linguistic structure in language models
We study feature interactions in the context of feature attribution methods for post-hoc
interpretability. In interpretability research, getting to grips with feature interactions is …
interpretability. In interpretability research, getting to grips with feature interactions is …
Efficient few-shot machine learning for classification of EBSD patterns
Deep learning is quickly becoming a standard approach to solving a range of materials
science objectives, particularly in the field of computer vision. However, labeled datasets …
science objectives, particularly in the field of computer vision. However, labeled datasets …
Using Shapley values and variational autoencoders to explain predictive models with dependent mixed features
Shapley values are today extensively used as a model-agnostic explanation framework to
explain complex predictive machine learning models. Shapley values have desirable …
explain complex predictive machine learning models. Shapley values have desirable …
[HTML][HTML] Exact Shapley values for local and model-true explanations of decision tree ensembles
TW Campbell, H Roder, RW Georgantas III… - Machine Learning with …, 2022 - Elsevier
Additive feature explanations using Shapley values have become popular for providing
transparency into the relative importance of each feature to an individual prediction of a …
transparency into the relative importance of each feature to an individual prediction of a …
Misspecification and unreliable interpretations in psychology and social science.
MJ Vowels - Psychological Methods, 2023 - psycnet.apa.org
The replicability crisis has drawn attention to numerous weaknesses in psychology and
social science research practice. In this work we focus on three issues that cannot be …
social science research practice. In this work we focus on three issues that cannot be …
Comparison of machine learning and stress concentration factors‐based fatigue failure prediction in small‐scale butt‐welded joints
M Braun, L Kellner - Fatigue & fracture of engineering materials …, 2022 - Wiley Online Library
Fatigue behavior of welded joints is significantly influenced by numerous factors, for
example, local weld geometry. A representative quantity for the influence of the notch effect …
example, local weld geometry. A representative quantity for the influence of the notch effect …
Automated biomarker candidate discovery in imaging mass spectrometry data through spatially localized Shapley additive explanations
LEM Tideman, LG Migas, KV Djambazova… - Analytica Chimica …, 2021 - Elsevier
The search for molecular species that are differentially expressed between biological states
is an important step towards discovering promising biomarker candidates. In imaging mass …
is an important step towards discovering promising biomarker candidates. In imaging mass …
Ultra-marginal feature importance: Learning from data with causal guarantees
Scientists frequently prioritize learning from data rather than training the best possible
model; however, research in machine learning often prioritizes the latter. Marginal …
model; however, research in machine learning often prioritizes the latter. Marginal …