Provably Better Explanations with Optimized Aggregation of Feature Attributions
- URL: http://arxiv.org/abs/2406.05090v1
- Date: Fri, 7 Jun 2024 17:03:43 GMT
- Title: Provably Better Explanations with Optimized Aggregation of Feature Attributions
- Authors: Thomas Decker, Ananta R. Bhattarai, Jindong Gu, Volker Tresp, Florian Buettner,
- Abstract summary: Using feature attributions for post-hoc explanations is a common practice to understand and verify the predictions of opaque machine learning models.
We propose a novel approach to derive optimal convex combinations of feature attributions that yield provable improvements of desired quality criteria.
- Score: 36.22433695108499
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Using feature attributions for post-hoc explanations is a common practice to understand and verify the predictions of opaque machine learning models. Despite the numerous techniques available, individual methods often produce inconsistent and unstable results, putting their overall reliability into question. In this work, we aim to systematically improve the quality of feature attributions by combining multiple explanations across distinct methods or their variations. For this purpose, we propose a novel approach to derive optimal convex combinations of feature attributions that yield provable improvements of desired quality criteria such as robustness or faithfulness to the model behavior. Through extensive experiments involving various model architectures and popular feature attribution techniques, we demonstrate that our combination strategy consistently outperforms individual methods and existing baselines.
Related papers
- Learning Joint Models of Prediction and Optimization [56.04498536842065]
Predict-Then-Then framework uses machine learning models to predict unknown parameters of an optimization problem from features before solving.
This paper proposes an alternative method, in which optimal solutions are learned directly from the observable features by joint predictive models.
arXiv Detail & Related papers (2024-09-07T19:52:14Z) - Pattern based learning and optimisation through pricing for bin packing problem [50.83768979636913]
We argue that when problem conditions such as the distributions of random variables change, the patterns that performed well in previous circumstances may become less effective.
We propose a novel scheme to efficiently identify patterns and dynamically quantify their values for each specific condition.
Our method quantifies the value of patterns based on their ability to satisfy constraints and their effects on the objective value.
arXiv Detail & Related papers (2024-08-27T17:03:48Z) - Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble [11.542472900306745]
Multi-Comprehension (MC) Ensemble is proposed as a strategy to augment the Out-of-Distribution (OOD) feature representation field.
Our experimental results demonstrate the superior performance of the MC Ensemble strategy in OOD detection.
This underscores the effectiveness of our proposed approach in enhancing the model's capability to detect instances outside its training distribution.
arXiv Detail & Related papers (2024-03-24T18:43:04Z) - Towards Optimal Feature-Shaping Methods for Out-of-Distribution
Detection [36.316424348556154]
Feature shaping is a family of methods that exhibit state-of-the-art performance for out-of-distribution (OOD) detection.
We propose a concrete reduction of the framework with a simple piecewise constant shaping function.
We show that our method improves the generalization ability of OOD detection across a large variety of datasets.
arXiv Detail & Related papers (2024-02-01T18:59:22Z) - Hierarchical Ensemble-Based Feature Selection for Time Series Forecasting [0.0]
We introduce a novel ensemble approach for feature selection based on hierarchical stacking for non-stationarity.
Our approach exploits the co-dependency between features using a hierarchical structure.
The effectiveness of the approach is demonstrated on synthetic and well-known real-life datasets.
arXiv Detail & Related papers (2023-10-26T16:40:09Z) - Consistent Explanations in the Face of Model Indeterminacy via
Ensembling [12.661530681518899]
This work addresses the challenge of providing consistent explanations for predictive models in the presence of model indeterminacy.
We introduce ensemble methods to enhance the consistency of the explanations provided in these scenarios.
Our findings highlight the importance of considering model indeterminacy when interpreting explanations.
arXiv Detail & Related papers (2023-06-09T18:45:43Z) - Investigating Ensemble Methods for Model Robustness Improvement of Text
Classifiers [66.36045164286854]
We analyze a set of existing bias features and demonstrate there is no single model that works best for all the cases.
By choosing an appropriate bias model, we can obtain a better robustness result than baselines with a more sophisticated model design.
arXiv Detail & Related papers (2022-10-28T17:52:10Z) - The effectiveness of factorization and similarity blending [0.0]
Collaborative Filtering (CF) is a technique which allows to leverage past users' preferences data to identify behavioural patterns and exploit them to predict custom recommendations.
We show that blending factorization-based and similarity-based approaches can lead to a significant error decrease (-9.4%) on stand-alone models.
We propose a novel extension of a similarity model, SCSR, which consistently reduce the complexity of the original algorithm.
arXiv Detail & Related papers (2022-09-16T13:11:27Z) - HyperImpute: Generalized Iterative Imputation with Automatic Model
Selection [77.86861638371926]
We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models.
We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
arXiv Detail & Related papers (2022-06-15T19:10:35Z) - Trusted Multi-View Classification [76.73585034192894]
We propose a novel multi-view classification method, termed trusted multi-view classification.
It provides a new paradigm for multi-view learning by dynamically integrating different views at an evidence level.
The proposed algorithm jointly utilizes multiple views to promote both classification reliability and robustness.
arXiv Detail & Related papers (2021-02-03T13:30:26Z)
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.