Lifting aims at improving the efficiency of probabilistic inference by exploiting symmetries in the model. Various methods for lifted probabilistic inference have been proposed, but our understanding of these methods and the relationships between them is still limited, compared to their propositional counterparts. The only existing theoretical characterization of lifting is a completeness result for weighted first-order model counting. This paper addresses the question whether the same completeness result holds for other lifted inference algorithms. We answer this question positively for lifted variable elimination (LVE). Our proof relies on introducing a novel inference operator for LVE.

Lifting attempts to speedup probabilistic inference by exploiting symmetries in the model. Exact lifted inference methods, like their propositional counterparts, work by recursively decomposing the model and the problem. In the propositional case, there exist formal structures, such as decomposition trees (dtrees), that represent such a decomposition and allow us to determine the complexity of inference a priori. However, there is currently no equivalent structure nor analogous complexity results for lifted inference. In this paper, we introduce FO-dtrees, which upgrade propositional dtrees to the first-order level. We show how these trees can characterize a lifted inference solution for a probabilistic logical model (in terms of a sequence of lifted operations), and make a theoretical analysis of the complexity of lifted inference in terms of the novel notion of lifted width for the tree.

Lifted probabilistic inference algorithms exploit regularities in the structure of graphical models to perform inference more efficiently. More specifically, they identify groups of interchangeable variables and perform inference once per group, as opposed to once per variable. The groups are defined by means of constraints, so the flexibility of the grouping is determined by the expressivity of the constraint language. Existing approaches for exact lifted inference use specific languages for (in)equality constraints, which often have limited expressivity. In this article, we decouple lifted inference from the constraint language. We define operators for lifted inference in terms of relational algebra operators, so that they operate on the semantic level (the constraints' extension) rather than on the syntactic level, making them language-independent. As a result, lifted inference can be performed using more powerful constraint languages, which provide more opportunities for lifting. We empirically demonstrate that this can improve inference efficiency by orders of magnitude, allowing exact inference where until now only approximate inference was feasible.

Probabilistic logical languages provide powerful formalisms for knowledge representation and learning. Yet performing inference in these languages is extremely costly, especially if it is done at the propositional level. Lifted inference algorithms, which avoid repeated computation by treating indistinguishable groups of objects as one, help mitigate this cost. Seeking inspiration from logical inference, where lifted inference (e.g., resolution) is commonly performed, we develop a model theoretic approach to probabilistic lifted inference. Our algorithm compiles a first-order probabilistic theory into a first-order deterministic decomposable negation normal form (d-DNNF) circuit. Compilation offers the advantage that inference is polynomial in the size of the circuit. Furthermore, by borrowing techniques from the knowledge compilation literature our algorithm effectively exploits the logical structure (e.g., context-specific independencies) within the first-order model, which allows more computation to be done at the lifted level. An empirical comparison demonstrates the utility of the proposed approach.

Information overload is no longer news; the explosive growth of the Internet has made this issue increasingly serious for Web users. Users are very often overwhelmed by the huge amount of information and are faced with a big challenge to find the most relevant information in the right time. Recommender systems aim at pruning this information space and directing users toward the items that best meet their needs and interests. Web Recommendation has been an active application area in Web Mining and Machine Learning research. In this paper we propose a novel machine learning perspective toward the problem, based on reinforcement learning. Unlike other recommender systems, our system does not use the static patterns discovered from web usage data, instead it learns to make recommendations as the actions it performs in each situation. We model the problem as Q-Learning while employing concepts and techniques commonly applied in the web usage mining domain. We propose that the reinforcement learning paradigm provides an appropriate model for the recommendation problem, as well as a framework in which the system constantly interacts with the user and learns from her behavior. Our experimental evaluations support our claims and demonstrate how this approach can improve the quality of web recommendations.