English
Related papers

Related papers: Motivating explanations in Bayesian networks using…

200 papers

A salient approach to interpretable machine learning is to restrict modeling to simple models. In the Bayesian framework, this can be pursued by restricting the model structure and prior to favor interpretable models. Fundamentally,…

Machine Learning · Computer Science 2020-09-08 Homayun Afrabandpey , Tomi Peltola , Juho Piironen , Aki Vehtari , Samuel Kaski

Causal models are crucial for understanding complex systems and identifying causal relationships among variables. Even though causal models are extremely popular, conditional probability calculation of formulas involving interventions pose…

Artificial Intelligence · Computer Science 2024-05-24 Sainyam Galhotra , Joseph Y. Halpern

Improved computational power has enabled different disciplines to predict causal relationships among modeled variables using Bayesian network inference. While many alternative algorithms have been proposed to improve the efficiency and…

Machine Learning · Statistics 2025-08-19 Habibolla Latifizadeh , Anika C. Pirkey , Alanna Gould , David J. Klinke

We introduce LAMP (Local Attribution Mapping Probe), a method that shines light onto a black-box language model's decision surface and studies how reliably a model maps its stated reasons to its reported predictions by approximating a…

Machine Learning · Computer Science 2026-04-28 Ryan Chen , Youngmin Ko , Zeyu Zhang , Catherine Cho , Sunny Chung , Mauro Giuffré , Dennis L. Shung , Bradly C. Stadie

This paper describes a decision theoretic formulation of learning the graphical structure of a Bayesian Belief Network from data. This framework subsumes the standard Bayesian approach of choosing the model with the largest posterior…

Artificial Intelligence · Computer Science 2013-02-01 Paola Sebastiani , Marco Ramoni

The widespread use of black-box AI models has raised the need for algorithms and methods that explain the decisions made by these models. In recent years, the AI research community is increasingly interested in models' explainability since…

Computer Vision and Pattern Recognition · Computer Science 2022-09-28 Savvas Karatsiolis , Andreas Kamilaris

We study the computations that Bayesian agents undertake when exchanging opinions over a network. The agents act repeatedly on their private information and take myopic actions that maximize their expected utility according to a fully…

Statistics Theory · Mathematics 2022-01-21 Jan Hązła , Ali Jadbabaie , Elchanan Mossel , M. Amin Rahimian

Independence and conditional independence are fundamental concepts for reasoning about groups of random variables in probabilistic programs. Verification methods for independence are still nascent, and existing methods cannot handle…

Logic in Computer Science · Computer Science 2021-05-04 Jialu Bao , Simon Docherty , Justin Hsu , Alexandra Silva

Most Relevant Explanation (MRE) is a method for finding multivariate explanations for given evidence in Bayesian networks [12]. This paper studies the theoretical properties of MRE and develops an algorithm for finding multiple top MRE…

Artificial Intelligence · Computer Science 2012-05-14 Changhe Yuan , Xiaolu Liu , Tsai-Ching Lu , Heejin Lim

The widespread adoption of algorithmic decision-making systems has brought about the necessity to interpret the reasoning behind these decisions. The majority of these systems are complex black box models, and auxiliary models are often…

Human-Computer Interaction · Computer Science 2022-02-28 Md Naimul Hoque , Klaus Mueller

In AI and law, systems that are designed for decision support should be explainable when pursuing justice. In order for these systems to be fair and responsible, they should make correct decisions and make them using a sound and transparent…

Artificial Intelligence · Computer Science 2021-05-17 Cor Steging , Silja Renooij , Bart Verheij

Selective rationalization improves neural network interpretability by identifying a small subset of input features -- the rationale -- that best explains or supports the prediction. A typical rationalization criterion, i.e. maximum mutual…

Machine Learning · Computer Science 2020-03-24 Shiyu Chang , Yang Zhang , Mo Yu , Tommi S. Jaakkola

Bayesian models are a powerful tool for studying complex data, allowing the analyst to encode rich hierarchical dependencies and leverage prior information. Most importantly, they facilitate a complete characterization of uncertainty…

Machine Learning · Statistics 2023-04-25 Steven Winter , Trevor Campbell , Lizhen Lin , Sanvesh Srivastava , David B. Dunson

We consider a decision network on an undirected graph in which each node corresponds to a decision variable, and each node and edge of the graph is associated with a reward function whose value depends only on the variables of the…

Probability · Mathematics 2009-12-03 David Gamarnik , David Goldberg , Theophane Weber

We describe a representation and a set of inference methods that combine logic programming techniques with probabilistic network representations for uncertainty (influence diagrams). The techniques emphasize the dynamic construction and…

Artificial Intelligence · Computer Science 2013-04-11 John S. Breese , Edison Tse

We present an automatic classification method for astronomical catalogs with missing data. We use Bayesian networks, a probabilistic graphical model, that allows us to perform inference to pre- dict missing values given observed data and…

Instrumentation and Methods for Astrophysics · Physics 2013-10-30 Karim Pichara , Pavlos Protopapas

Two prominent challenges in explainability research involve 1) the nuanced evaluation of explanations and 2) the modeling of missing information through baseline representations. The existing literature introduces diverse evaluation…

Machine Learning · Computer Science 2024-12-24 Oren Barkan , Yehonatan Elisha , Jonathan Weill , Noam Koenigstein

Bayesian networks are widely used to learn and reason about the dependence structure of discrete variables. However, they are only capable of formally encoding symmetric conditional independence, which in practice is often too strict to…

Artificial Intelligence · Computer Science 2023-01-03 Manuele Leonelli , Gherardo Varando

Modern instance-based model-agnostic explanation methods (LIME, SHAP, L2X) are of great use in data-heavy industries for model diagnostics, and for end-user explanations. These methods generally return either a weighting or subset of input…

Machine Learning · Computer Science 2019-12-03 Matt Chapman-Rounds , Marc-Andre Schulz , Erik Pazos , Konstantinos Georgatzis

In this paper we examine the problem of inference in Bayesian Networks with discrete random variables that have very large or even unbounded domains. For example, in a domain where we are trying to identify a person, we may have variables…

Artificial Intelligence · Computer Science 2012-12-12 Rita Sharma , David L Poole