KompaRe
Authors:
Open Access
- 14 August 2021
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3308-3318
Abstract
Reasoning is a fundamental capability for harnessing valuable insight, knowledge and patterns from knowledge graphs. Existing work has primarily been focusing on point-wise reasoning, including search, link prediction, entity prediction, subgraph matching and so on. This paper introduces comparative reasoning over knowledge graphs, which aims to infer the commonality and inconsistency with respect to multiple pieces of clues. We envision that the comparative reasoning will complement and expand the existing point-wise reasoning over knowledge graphs. In detail, we develop KompaRe, the first of its kind prototype system that provides comparative reasoning capability over large knowledge graphs. We present both the system architecture and its core algorithms, including knowledge segment extraction, pairwise reasoning and collective reasoning. Empirical evaluations demonstrate the efficacy of the proposed KompaRe.Keywords
Funding Information
- NSF (National Science Foundation) (1939725)
This publication has 12 references indexed in Scilit:
- A review: Knowledge reasoning over knowledge graphExpert Systems with Applications, 2020
- ADMIRING: Adversarial Multi-network Mining2019
- Answering Natural Language Questions by Subgraph Matching over Knowledge GraphsIEEE Transactions on Knowledge and Data Engineering, 2017
- Object Detection Meets Knowledge Graphs2017
- DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning2017
- Correction: Computational Fact Checking from Knowledge NetworksPLOS ONE, 2015
- Querying Knowledge Graphs by Example Entity TuplesIEEE Transactions on Knowledge and Data Engineering, 2015
- Schemaless and structureless graph queryingProceedings of the VLDB Endowment, 2014
- Yago2007
- Center-piece subgraphs2006