Generalized Reasoning with Graph Neural Networks by Relational Bayesian Network Encodings

Raffaele Pojer, Andrea Passerini, Manfred Jaeger

Research output: Contribution to conference without publisher/journalPaper without publisher/journalResearchpeer-review

9 Downloads (Pure)

Abstract

Graph neural networks (GNNs) and statistical relational learning are two different approaches to learning with graph data. The former can provide highly accurate models for specific tasks when sufficient training data is available, whereas the latter supports a wider range of reasoning types, and can incorporate manual specifications of interpretable domain knowledge. In this paper we present a method to embed GNNs in a statistical relational learning framework, such that the predictive model represented by the GNN becomes part of a full generative model. This model then supports a wide range of queries, including general conditional probability queries, and computing most probable configurations of unobserved node attributes or edges. In particular, we demonstrate how this latter type of queries can be used to obtain model-level explanations of a GNN in a flexible and interactive manner.
Original languageEnglish
Publication date2023
Number of pages12
Publication statusPublished - 2023
EventThe Second Learning on Graphs Conference - Online
Duration: 27 Nov 202330 Nov 2023
Conference number: 2
https://logconference.org/

Conference

ConferenceThe Second Learning on Graphs Conference
Number2
LocationOnline
Period27/11/202330/11/2023
Internet address

Fingerprint

Dive into the research topics of 'Generalized Reasoning with Graph Neural Networks by Relational Bayesian Network Encodings'. Together they form a unique fingerprint.

Cite this