English
Related papers

Related papers: Relevant Explanations: Allowing Disjunctive Assign…

200 papers

Independence-based (IB) assignments to Bayesian belief networks were originally proposed as abductive explanations. IB assignments assign fewer variables in abductive explanations than do schemes assigning values to all evidentially…

Artificial Intelligence · Computer Science 2013-02-28 Eugene Santos , Solomon Eyal Shimony

In decision support systems the motivation and justification of the system's diagnosis or classification is crucial for the acceptance of the system by the human user. In Bayesian networks a diagnosis or classification is typically…

Artificial Intelligence · Computer Science 2022-08-08 Johan Kwisthout

Irrelevance-based partial MAPs are useful constructs for domain-independent explanation using belief networks. We look at two definitions for such partial MAPs, and prove important properties that are useful in designing algorithms for…

Artificial Intelligence · Computer Science 2013-03-26 Solomon Eyal Shimony

A major inference task in Bayesian networks is explaining why some variables are observed in their particular states using a set of target variables. Existing methods for solving this problem often generate explanations that are either too…

Artificial Intelligence · Computer Science 2014-01-17 Changhe Yuan , Heejin Lim , Tsai-Ching Lu

This paper analyzes irrelevance and independence relations in graphical models associated with convex sets of probability distributions (called Quasi-Bayesian networks). The basic question in Quasi-Bayesian networks is, How can…

Artificial Intelligence · Computer Science 2013-02-01 Fabio Gagliardi Cozman

A credal network under epistemic irrelevance is a generalised type of Bayesian network that relaxes its two main building blocks. On the one hand, the local probabilities are allowed to be partially specified. On the other hand, the…

Artificial Intelligence · Computer Science 2017-03-20 Jasper De Bock

Given a machine learning (ML) model and a prediction, explanations can be defined as sets of features which are sufficient for the prediction. In some applications, and besides asking for an explanation, it is also critical to understand…

Machine Learning · Computer Science 2023-02-08 Xuanxiang Huang , Martin C. Cooper , Antonio Morgado , Jordi Planes , Joao Marques-Silva

One of the benefits of belief networks and influence diagrams is that so much knowledge is captured in the graphical structure. In particular, statements of conditional irrelevance (or independence) can be verified in time linear in the…

Artificial Intelligence · Computer Science 2013-02-01 Ross D. Shachter

Dependency networks (Heckerman et al., 2000) provide a flexible framework for modeling complex systems with many variables by combining independently learned local conditional distributions through pseudo-Gibbs sampling. Despite their…

Machine Learning · Computer Science 2026-04-02 Kazuya Takabatake , Shotaro Akaho

We present a new approach to credal nets, which are graphical models that generalise Bayesian nets to imprecise probability. Instead of applying the commonly used notion of strong independence, we replace it by the weaker notion of…

Artificial Intelligence · Computer Science 2012-08-07 Jasper De Bock , Gert de Cooman

Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative…

Machine Learning · Computer Science 2019-11-06 Mengjiao Yang , Been Kim

Teddy Seidenfeld has been arguing for quite a long time that binary preference models are not powerful enough to deal with a number of crucial aspects of imprecision and indeterminacy in uncertain inference and decision making. It is at his…

Artificial Intelligence · Computer Science 2021-02-23 Jasper De Bock , Gert de Cooman

Attribution methods aim to explain a neural network's prediction by highlighting the most relevant image areas. A popular approach is to backpropagate (BP) a custom relevance score using modified rules, rather than the gradient. We analyze…

Machine Learning · Computer Science 2024-02-20 Leon Sixt , Maximilian Granz , Tim Landgraf

This paper introduces a computational framework for reasoning in Bayesian belief networks that derives significant advantages from focused inference and relevance reasoning. This framework is based on d -separation and other simple and…

Artificial Intelligence · Computer Science 2013-02-08 Yan Lin , Marek J. Druzdzel

Feature attribution is often loosely presented as the process of selecting a subset of relevant features as a rationale of a prediction. Task-dependent by nature, precise definitions of "relevance" encountered in the literature are however…

Machine Learning · Computer Science 2021-07-12 Darius Afchar , Romain Hennequin , Vincent Guigue

Layer-wise Relevance Propagation (LRP) and saliency maps have been recently used to explain the predictions of Deep Learning models, specifically in the domain of text classification. Given different attribution-based explanations to…

Information Retrieval · Computer Science 2018-12-04 Wenting Xiong , Iftitahu Ni'mah , Juan M. G. Huesca , Werner van Ipenburg , Jan Veldsink , Mykola Pechenizkiy

Conditional-independence-based discovery uses statistical tests to identify a graphical model that represents the independence structure of variables in a dataset. These tests, however, can be unreliable, and algorithms are sensitive to…

Machine Learning · Computer Science 2026-04-21 Philipp M. Faller , Dominik Janzing

Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history. In critical applications, it is vital to identify which…

Computation and Language · Computer Science 2026-02-03 Poushali Sengupta , Shashi Raj Pandey , Sabita Maharjan , Frank Eliassen

The interest in complex deep neural networks for computer vision applications is increasing. This leads to the need for improving the interpretable capabilities of these models. Recent explanation methods present visualizations of the…

Machine Learning · Computer Science 2020-04-24 Dan Valle , Tiago Pimentel , Adriano Veloso

In causal inference confounding may be controlled either through regression adjustment in an outcome model, or through propensity score adjustment or inverse probability of treatment weighting, or both. The latter approaches, which are…

Methodology · Statistics 2017-01-17 Olli Saarela , Léo R. Belzile , David A. Stephens
‹ Prev 1 2 3 10 Next ›