RKHS-SHAP: Shapley Values for Kernel Methods
- URL: http://arxiv.org/abs/2110.09167v1
- Date: Mon, 18 Oct 2021 10:35:36 GMT
- Title: RKHS-SHAP: Shapley Values for Kernel Methods
- Authors: Siu Lun Chau, Javier Gonzalez, Dino Sejdinovic
- Abstract summary: We propose an attribution method for kernel machines that can efficiently compute both emphInterventional and emphObservational Shapley values
We show theoretically that our method is robust with respect to local perturbations - a key yet often overlooked desideratum for interpretability.
- Score: 17.52161019964009
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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, a coalition game theoretical framework that has previously been
applied to different machine learning model interpretation tasks, such as
linear models, tree ensembles and deep networks. By analysing Shapley values
from a functional perspective, we propose \textsc{RKHS-SHAP}, an attribution
method for kernel machines that can efficiently compute both
\emph{Interventional} and \emph{Observational Shapley values} using kernel mean
embeddings of distributions. We show theoretically that our method is robust
with respect to local perturbations - a key yet often overlooked desideratum
for interpretability. Further, we propose \emph{Shapley regulariser},
applicable to a general empirical risk minimisation framework, allowing
learning while controlling the level of specific feature's contributions to the
model. We demonstrate that the Shapley regulariser enables learning which is
robust to covariate shift of a given feature and fair learning which controls
the Shapley values of sensitive features.
Related papers
- Improving the Sampling Strategy in KernelSHAP [0.8057006406834466]
KernelSHAP framework enables us to approximate the Shapley values using a sampled subset of weighted conditional expectations.
We propose three main novel contributions: a stabilizing technique to reduce the variance of the weights in the current state-of-the-art strategy, a novel weighing scheme that corrects the Shapley kernel weights based on sampled subsets, and a straightforward strategy that includes the important subsets and integrates them with the corrected Shapley kernel weights.
arXiv Detail & Related papers (2024-10-07T10:02:31Z) - Variational Shapley Network: A Probabilistic Approach to Self-Explaining
Shapley values with Uncertainty Quantification [2.6699011287124366]
Shapley values have emerged as a foundational tool in machine learning (ML) for elucidating model decision-making processes.
We introduce a novel, self-explaining method that simplifies the computation of Shapley values significantly, requiring only a single forward pass.
arXiv Detail & Related papers (2024-02-06T18:09:05Z) - Fast Shapley Value Estimation: A Unified Approach [71.92014859992263]
We propose a straightforward and efficient Shapley estimator, SimSHAP, by eliminating redundant techniques.
In our analysis of existing approaches, we observe that estimators can be unified as a linear transformation of randomly summed values from feature subsets.
Our experiments validate the effectiveness of our SimSHAP, which significantly accelerates the computation of accurate Shapley values.
arXiv Detail & Related papers (2023-11-02T06:09:24Z) - Efficient Shapley Values Estimation by Amortization for Text
Classification [66.7725354593271]
We develop an amortized model that directly predicts each input feature's Shapley Value without additional model evaluations.
Experimental results on two text classification datasets demonstrate that our amortized model estimates Shapley Values accurately with up to 60 times speedup.
arXiv Detail & Related papers (2023-05-31T16:19:13Z) - Lyapunov Density Models: Constraining Distribution Shift in
Learning-Based Control [64.61499213110334]
We seek a mechanism to constrain the agent to states and actions that resemble those that it was trained on.
In control theory, Lyapunov stability and control-invariant sets allow us to make guarantees about controllers.
density models allow us to estimate the training data distribution.
arXiv Detail & Related papers (2022-06-21T16:49:09Z) - Exact Shapley Values for Local and Model-True Explanations of Decision
Tree Ensembles [0.0]
We consider the application of Shapley values for explaining decision tree ensembles.
We present a novel approach to Shapley value-based feature attribution that can be applied to random forests and boosted decision trees.
arXiv Detail & Related papers (2021-12-16T20:16:02Z) - Scaling Structured Inference with Randomization [64.18063627155128]
We propose a family of dynamic programming (RDP) randomized for scaling structured models to tens of thousands of latent states.
Our method is widely applicable to classical DP-based inference.
It is also compatible with automatic differentiation so can be integrated with neural networks seamlessly.
arXiv Detail & Related papers (2021-12-07T11:26:41Z) - groupShapley: Efficient prediction explanation with Shapley values for
feature groups [2.320417845168326]
Shapley values has established itself as one of the most appropriate and theoretically sound frameworks for explaining predictions from machine learning models.
The main drawback with Shapley values is that its computational complexity grows exponentially in the number of input features.
The present paper introduces groupShapley: a conceptually simple approach for dealing with the aforementioned bottlenecks.
arXiv Detail & Related papers (2021-06-23T08:16:14Z) - Fast Hierarchical Games for Image Explanations [78.16853337149871]
We present a model-agnostic explanation method for image classification based on a hierarchical extension of Shapley coefficients.
Unlike other Shapley-based explanation methods, h-Shap is scalable and can be computed without the need of approximation.
We compare our hierarchical approach with popular Shapley-based and non-Shapley-based methods on a synthetic dataset, a medical imaging scenario, and a general computer vision problem.
arXiv Detail & Related papers (2021-04-13T13:11:02Z) - A Distributional Analysis of Sampling-Based Reinforcement Learning
Algorithms [67.67377846416106]
We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes.
We show that value-based methods such as TD($lambda$) and $Q$-Learning have update rules which are contractive in the space of distributions of functions.
arXiv Detail & Related papers (2020-03-27T05:13:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.