paper-with-me

홈 › Papers

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 explanations often present different aspects of the model's behavior. In this research manuscript, we explore the potential of ensembling explanations generated by deep classification models using convolutional model. Through experimentation and analysis, we aim to investigate the implications of combining explanations to uncover a more coherent and reliable patterns of the model's behavior, leading to the possibility of evaluating the representation learned by the model. With our method, we can uncover problems of under-representation of images in a certain class. Moreover, we discuss other side benefits like features' reduction by replacing the original image with its explanations resulting in the removal of some sensitive information. Through the use of carefully selected evaluation metrics from the Quantus library, we demonstrated the method's superior performance in terms of Localisation and Faithfulness, compared to individual explanations.

📄 PDF Abstract BibTeX arXiv:2404.10387

Code (0)

등록된 구현이 없습니다.

Tasks

Explainable artificial intelligence

Similar Papers 제목 키워드 기반

Consistent Explanations in the Face of Model Indeterminacy via Ensembling

2023-06-09 · Dan Ley, Leonard Tang, Matthew Nazari, Hongjin Lin 외

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 f…

Do explanations generalize across large reasoning models?

2026-01-16 · Koyena Pal, David Bau, Chandan Singh arxiv

Large reasoning models (LRMs) produce a textual chain of thought (CoT) in the process of solving a problem, which serves as a potentially powerful tool to understand the problem by surfacing a human-readable, natural-lan…

Reinforcement Learning

Aggregate Models, Not Explanations: Improving Feature Importance Estimation

2026-02-12 · Joseph Paillard, Angel Reyero Lobo, Denis A. Engemann, Bertrand Thirion arxiv

Feature-importance methods show promise in transforming machine learning models from predictive engines into tools for scientific discovery. However, due to data sampling and algorithmic stochasticity, expressive models …

Feature Importance

Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning

2022-02-17 · Juntao Tan, Shijie Geng, Zuohui Fu, Yingqiang Ge 외

Structural data well exists in Web applications, such as social networks in social media, citation networks in academic websites, and threads data in online forums. Due to the complex topology, it is difficult to process…

Causal InferencecounterfactualGraph Neural Network

Deep Integrated Explanations

2023-10-23 · Oren Barkan, Yehonatan Elisha, Jonathan Weill, Yuval Asher 외

This paper presents Deep Integrated Explanations (DIX) - a universal method for explaining vision models. DIX generates explanation maps by integrating information from the intermediate representations of the model, coup…