Related papers: Counterfactual Causality in Networks
To act safely and ethically in the real world, agents must be able to reason about harm and avoid harmful actions. However, to date there is no statistical method for measuring harm and factoring it into algorithmic decisions. In this paper…
Explainable Artificial Intelligence and Formal Argumentation have received significant attention in recent years. Argumentation-based systems often lack explainability while supporting decision-making processes. Counterfactual and…
There exists three main areas of study inside of the field of predictive maintenance: anomaly detection, fault diagnosis, and remaining useful life prediction. Notably, anomaly detection alerts the stakeholder that an anomaly is occurring.…
Causality is omnipresent in scientists' verbalisations of their understanding, even though we have no formal consensual scientific definition for it. In Automata Networks, it suffices to say that automata "influence" one another to…
This study presents a novel framework for counterfactual user behavior forecasting that combines structural causal models with transformer-based generative artificial intelligence. To model fictitious situations, the method creates causal…
Although deep learning models have been successfully applied to a variety of tasks, due to the millions of parameters, they are becoming increasingly opaque and complex. In order to establish trust for their widespread commercial use, it is…
Recent work on counterfactual visual explanations has contributed to making artificial intelligence models more explainable by providing visual perturbation to flip the prediction. However, these approaches neglect the causal relationships…
Thinking in terms of causality helps us structure how different parts of a system depend on each other, and how interventions on one part of a system may result in changes to other parts. Therefore, formal models of causality are an…
We propose a formal model for counterfactual estimation with unobserved confounding in "data-rich" settings, i.e., where there are a large number of units and a large number of measurements per unit. Our model provides a bridge between the…
Machine learning models are increasingly used in areas such as loan approvals and hiring, yet they often function as black boxes, obscuring their decision-making processes. Transparency is crucial, and individuals need explanations to…
Network economics is the study of a rich class of equilibrium problems that occur in the real world, from traffic management to supply chains and two-sided online marketplaces. In this paper we explore causal inference in network economics,…
Causal reasoning is essential for understanding decision-making about the behaviour of complex `ecosystems' of systems that underpin modern society, with security -- including issues around correctness, safety, resilience, etc. -- typically…
There are some recent approaches and results about the use of answer-set programming for specifying counterfactual interventions on entities under classification, and reasoning about them. These approaches are flexible and modular in that…
Counterfactual reasoning and contextuality is defined and critically evaluated with regard to its nonempirical content. To this end, a uniqueness property of states, explosion views and link observables are introduced. If only a single…
We address the problem of causal interpretation of the graphical structure of Bayesian belief networks (BBNs). We review the concept of causality explicated in the domain of structural equations models and show that it is applicable to…
The ability to analyze network threats is very important in security research. Traditional approaches, involving sandboxing technology are limited to simulating a single host, missing local network attacks. This issue is addressed by…
We demonstrate, by a number of examples, that information-flow security properties can be proved from abstract architectural descriptions, that describe only the causal structure of a system and local properties of trusted components. We…
Safety critical systems strongly require the quality aspects of artificial intelligence including explainability. In this paper, we analyzed a trained network to extract features which mainly contribute the inference. Based on the analysis,…
We describe some recent approaches to score-based explanations for query answers in databases. The focus is on work done by the author and collaborators. Special emphasis is placed on the use of counterfactual reasoning for score…
Transparency is an essential requirement of machine learning based decision making systems that are deployed in real world. Often, transparency of a given system is achieved by providing explanations of the behavior and predictions of the…