Axiomatic Explainer Globalness via Optimal Transport
- URL: http://arxiv.org/abs/2411.01126v1
- Date: Sat, 02 Nov 2024 04:01:38 GMT
- Title: Axiomatic Explainer Globalness via Optimal Transport
- Authors: Davin Hill, Josh Bone, Aria Masoomi, Max Torop, Jennifer Dy,
- Abstract summary: We define a complexity measure for explainers, globalness, which enables deeper understanding of the distribution of explanations.
We prove that our proposed measure, Wasserstein Globalness, meets these criteria.
- Score: 3.2203930850666675
- License:
- Abstract: Explainability methods are often challenging to evaluate and compare. With a multitude of explainers available, practitioners must often compare and select explainers based on quantitative evaluation metrics. One particular differentiator between explainers is the diversity of explanations for a given dataset; i.e. whether all explanations are identical, unique and uniformly distributed, or somewhere between these two extremes. In this work, we define a complexity measure for explainers, globalness, which enables deeper understanding of the distribution of explanations produced by feature attribution and feature selection methods for a given dataset. We establish the axiomatic properties that any such measure should possess and prove that our proposed measure, Wasserstein Globalness, meets these criteria. We validate the utility of Wasserstein Globalness using image, tabular, and synthetic datasets, empirically showing that it both facilitates meaningful comparison between explainers and improves the selection process for explainability methods.
Related papers
- BEE: Metric-Adapted Explanations via Baseline Exploration-Exploitation [10.15605247436119]
Two prominent challenges in explainability research involve 1) the nuanced evaluation of explanations and 2) the modeling of missing information.
We propose Baseline Exploration-Exploitation (BEE) - a path-integration method that introduces randomness to the integration process.
BEE generates a comprehensive set of explanation maps, facilitating the selection of the best-performing explanation map.
arXiv Detail & Related papers (2024-12-23T12:19:03Z) - Discrete Subgraph Sampling for Interpretable Graph based Visual Question Answering [27.193336817953142]
We integrate different discrete subset sampling methods into a graph-based visual question answering system.
We show that the integrated methods effectively mitigate the performance trade-off between interpretability and answer accuracy.
We also conduct a human evaluation to assess the interpretability of the generated subgraphs.
arXiv Detail & Related papers (2024-12-11T10:18:37Z) - Rethinking Distance Metrics for Counterfactual Explainability [53.436414009687]
We investigate a framing for counterfactual generation methods that considers counterfactuals not as independent draws from a region around the reference, but as jointly sampled with the reference from the underlying data distribution.
We derive a distance metric, tailored for counterfactual similarity that can be applied to a broad range of settings.
arXiv Detail & Related papers (2024-10-18T15:06:50Z) - Extracting Interpretable Local and Global Representations from Attention
on Time Series [0.135975510645475]
This paper targets two transformer attention based interpretability methods working with local abstraction and global representation.
We distinguish local and global contexts, and provide a comprehensive framework for both general interpretation options.
arXiv Detail & Related papers (2023-09-16T00:51:49Z) - Enriching Disentanglement: From Logical Definitions to Quantitative Metrics [59.12308034729482]
Disentangling the explanatory factors in complex data is a promising approach for data-efficient representation learning.
We establish relationships between logical definitions and quantitative metrics to derive theoretically grounded disentanglement metrics.
We empirically demonstrate the effectiveness of the proposed metrics by isolating different aspects of disentangled representations.
arXiv Detail & Related papers (2023-05-19T08:22:23Z) - Evaluating the Robustness of Interpretability Methods through
Explanation Invariance and Equivariance [72.50214227616728]
Interpretability methods are valuable only if their explanations faithfully describe the explained model.
We consider neural networks whose predictions are invariant under a specific symmetry group.
arXiv Detail & Related papers (2023-04-13T17:59:03Z) - Explanation Selection Using Unlabeled Data for Chain-of-Thought
Prompting [80.9896041501715]
Explanations that have not been "tuned" for a task, such as off-the-shelf explanations written by nonexperts, may lead to mediocre performance.
This paper tackles the problem of how to optimize explanation-infused prompts in a blackbox fashion.
arXiv Detail & Related papers (2023-02-09T18:02:34Z) - Partial Order in Chaos: Consensus on Feature Attributions in the
Rashomon Set [50.67431815647126]
Post-hoc global/local feature attribution methods are being progressively employed to understand machine learning models.
We show that partial orders of local/global feature importance arise from this methodology.
We show that every relation among features present in these partial orders also holds in the rankings provided by existing approaches.
arXiv Detail & Related papers (2021-10-26T02:53:14Z) - Discriminative Attribution from Counterfactuals [64.94009515033984]
We present a method for neural network interpretability by combining feature attribution with counterfactual explanations.
We show that this method can be used to quantitatively evaluate the performance of feature attribution methods in an objective manner.
arXiv Detail & Related papers (2021-09-28T00:53:34Z)
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.