Lifting factor graphs with some unknown factors for new individuals

作     者：Luttermann, Malte Moeller, Ralf Gehrke, Marcel 

作者机构：German Res Ctr Artificial Intelligence DFKI Ratzeburger Allee 160 D-23562 Lubeck Germany Univ Hamburg Inst Humanities Ctr Artificial Intelligence Warburgstr 28 D-20354 Hamburg Germany 

出 版 物：《INTERNATIONAL JOURNAL OF APPROXIMATE REASONING》 (Int J Approximate Reasoning)

年 卷 期：2025年第179卷

核心收录：

学科分类：07[理学] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 070101[理学-基础数学] 

基　　金：BMBF project [ECSQARU 2023, 16KISA057] 16KISA050K 

主　　题：Probabilistic graphical models Factor graphs Lifted inference 

摘      要：Lifting exploits symmetries in probabilistic graphical models by using a representative for indistinguishable objects, allowing to carry out query answering more efficiently while maintaining exact answers. In this paper, we investigate how lifting enables us to perform probabilistic inference for factor graphs containing unknown factors, i.e., factors whose underlying function of potential mappings is unknown. We present the Lifting Factor Graphs with Some Unknown Factors (LIFAGU) algorithm to identify indistinguishable subgraphs in a factor graph containing unknown factors, thereby enabling the transfer of known potentials to unknown potentials to ensure a well-defined semantics of the model and allow for (lifted) probabilistic inference. We further extend LIFAGU to incorporate additional background knowledge about groups of factors belonging to the same individual object. By incorporating such background knowledge, LIFAGU is able to further reduce the ambiguity of possible transfers of known potentials to unknown potentials.