Revision by Comparison for Ranking Functions

Abstract

Relational graph neural networks have garnered particular attention to encode graph context in knowledge graphs (KGs). Although they achieved competitive performance on small KGs, how to efficiently and effectively utilize graph context for large KGs remains an open problem. To this end, we propose the Relation-based Embedding Propagation (REP) method. It is a post-processing technique to adapt pre-trained KG embeddings with graph context. As relations in KGs are directional, we model the incoming head context and the outgoing tail context separately. Accordingly, we design relational context functions with no external parameters. Besides, we use averaging to aggregate context information, making REP more computation-efficient. We theoretically prove that such designs can avoid information distortion during propagation. Extensive experiments also demonstrate that REP has significant scalability while improving or maintaining prediction quality. Particularly, it averagely brings about 10% relative improvement to triplet-based embedding methods on OGBL-WikiKG2 and takes 5%-83% time to achieve comparable results as the state-of-the-art GC-OTE.

Implementing Bounded Revision via Lexicographic Revision and C-revision

“…There have been several approaches to belief revision with input information that is accompanied by some kind of supplementary information, see e.g. (Hunter 2021;Ammar and Ismail 2021;Sezgin and Kern-Isberner 2022), indicating trust or reliance towards the input information. In this paper, we present a revision method in a qualitative and a semi-quantitative framework based on Bounded Revision (BR) which was firstly introduced by (Rott 2012).…”