paper-with-me

홈 › Papers

Consistent Explanations in the Face of Model Indeterminacy via Ensembling

2023-06-09 · Dan Ley, Leonard Tang, Matthew Nazari, Hongjin Lin, Suraj Srinivas, Himabindu Lakkaraju

This work addresses the challenge of providing consistent explanations for predictive models in the presence of model indeterminacy, which arises due to the existence of multiple (nearly) equally well-performing models for a given dataset and task. Despite their similar performance, such models often exhibit inconsistent or even contradictory explanations for their predictions, posing challenges to end users who rely on these models to make critical decisions. Recognizing this issue, we introduce ensemble methods as an approach to enhance the consistency of the explanations provided in these scenarios. Leveraging insights from recent work on neural network loss landscapes and mode connectivity, we devise ensemble strategies to efficiently explore the underspecification set -- the set of models with performance variations resulting solely from changes in the random seed during training. Experiments on five benchmark financial datasets reveal that ensembling can yield significant improvements when it comes to explanation similarity, and demonstrate the potential of existing ensemble methods to explore the underspecification set efficiently. Our findings highlight the importance of considering model indeterminacy when interpreting explanations and showcase the effectiveness of ensembles in enhancing the reliability of explanations in machine learning.

📄 PDF Abstract BibTeX arXiv:2306.06193

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Recourse under Model Multiplicity via Argumentative Ensembling (Technical Report)

2023-12-22 · Junqi Jiang, Antonio Rago, Francesco Leofante, Francesca Toni

Model Multiplicity (MM) arises when multiple, equally performing machine learning models can be trained to solve the same prediction task. Recent studies show that models obtained under MM may produce inconsistent predic…

counterfactual

Visual Indeterminacy in GAN Art

2019-10-10 · Aaron Hertzmann

This paper explores visual indeterminacy as a description for artwork created with Generative Adversarial Networks (GANs). Visual indeterminacy describes images which appear to depict real scenes, but, on closer examinat…

Image Generation

Perspectives on Latent Factor Indeterminacy and its Implications for Data Representation

2026-06-27 · Carel F. W. Peeters arxiv

The common factor analytic model is related to Helmholtz and Boltzmann machines, can be conceived as a linear autoencoder, or can be thought of as a single-hidden-layer generative neural network. We thus consider it a ba…

Representation Learning

When Are Two Scores Better Than One? Investigating Ensembles of Diffusion Models

2026-01-16 · Raphaël Razafindralambo, Rémy Sun, Frédéric Precioso, Damien Garreau 외 arxiv

Diffusion models now generate high-quality, diverse samples, with an increasing focus on more powerful models. Although ensembling is a well-known way to improve supervised models, its application to unconditional score-…

CNN-based explanation ensembling for dataset, representation and explanations evaluation

2024-04-16 · Weronika Hryniewska-Guzik, Luca Longo, Przemysław Biecek

Explainable Artificial Intelligence has gained significant attention due to the widespread use of complex deep learning models in high-stake domains such as medicine, finance, and autonomous cars. However, different expl…

Explainable artificial intelligence