Magdalena Ivanovska

Subjective Networks: Perspectives and Challenges

Subjective logic is a formalism for reasoning under uncertain probabilistic information, with an explicit treatment of the uncertainty about the probability distributions. We introduce subjective networks as graph-based structures that generalize Bayesian networks to the theory of subjective logic. We discuss the perspectives of the subjective networks representation and the challenges of reasoning with them.

Joint Subjective Opinions

Subjective opinions generalize probability distributions by including degrees of uncertainty which reflect lack of confidence in the probabilities. This paper describes a method for computing the joint subjective opinion of two variables which can be generalized to a method for computing joint subjective opinions over multiple variables in a subjective Bayesian network. We show how the joint opinions can be marginalized to provide subjective opinions on a reduced number of variables. With an example we compare the marginalization of a joint opinion with subjective logic deduction which also produces a marginal opinion.

Subjective Bayesian Networks and Human-in-the-Loop Situational Understanding

In this paper we present a methodology to exploit human-machine coalitions for situational understanding. Situational understanding refers to the ability to relate relevant information and form logical conclusions, as well as identify gaps in information. This process for comprehension of the meaning information requires the ability to reason inductively, for which we will exploit the machines’ ability to ‘learn’ from data. However, important phenomena are often rare in occurrence with high degrees of uncertainty, thus severely limiting the availability of instance data for training, and hence the applicability of many machine learning approaches. Therefore, we present the benefits of Subjective Bayesian Networks—i.e., Bayesian Networks with imprecise probabilities—for situational understanding, and the role of conversational interfaces for supporting decision makers in the evolution of situational understanding.

Efficient belief propagation in second-order Bayesian networks for singly-connected graphs

Abstract Second-order Bayesian networks extend Bayesian networks by incorporating uncertainty in the conditional probabilities. This paper develops a method for inference in a binary second-order Bayesian network with a singly-connected graph that builds upon the message-passing algorithm for regular belief propagation by leveraging recent developments in subjective logic. The method applies the moment-matching approach to the Beta representation of the uncertain probabilities. We provide experimental analysis which shows that the introduced method effectively captures the bounds for the actual error in a consistent manner and, at the same time, does not decrease the efficiency of the performance compared to the other similar approaches.