Bowen Dong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bowen Dong has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Xueli Liu
College of Intelligence and Computing, Tianjin University, Tianjin, China
4 shared publications - Wenjun Wang
College of Intelligence and Computing, Tianjin University, Tianjin 300350, China
3 shared publications - Binrong Liu
College of Intelligence and Computing, Tianjin University, Tianjin, China
1 shared publication - Lifei Sun
Tianjin University
1 shared publication - Nannan Wu
College of Intelligence and Computing, Tianjin University, Tianjin, China
1 shared publication - Pengyue Jiang
Tianjin University
1 shared publication
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 2720-2729
Graph Joint Representation Learning for Sound and Scalable Instantiation
Knowledge graph reasoning is a fundamental problem in artificial intelligence, where rule-based methods provide strong interpretability but suffer from exponential symbolic search complexity, while existing neuro-symbolic approaches struggle to model complex Horn rules with rich topologies. We propose Rule–Graph Joint Representation Learning (RGRS), a unified neuro-symbolic framework that integrates rule-level reasoning with graph representation learning for scalable Horn rule instantiation. RGRS introduces logically constrained rule embeddings and dominance-aware subgraph representations, enabling embedding-guided structural pruning while preserving correctness through exact symbolic verification. By coupling continuous structural abstraction with deterministic matching in a filter–verify pipeline, RGRS effectively reduces the combinatorial search space without compromising logical semantics. Extensive experiments on large-scale knowledge graphs show that RGRS achieves consistently high accuracy with significant efficiency gains over symbolic and neuro-symbolic baselines, providing a principled bridge between symbolic reasoning and embedding-based efficiency.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 2720-2729
Open AccessGraph Joint Representation Learning for Sound and Scalable Instantiation
Knowledge graph reasoning is a fundamental problem in artificial intelligence, where rule-based methods provide strong interpretability but suffer from exponential symbolic search complexity, while existing neuro-symbolic approaches struggle to model complex Horn rules with rich topologies. We propose Rule–Graph Joint Representation Learning (RGRS), a unified neuro-symbolic framework that integrates rule-level reasoning with graph representation learning for scalable Horn rule instantiation. RGRS introduces logically constrained rule embeddings and dominance-aware subgraph representations, enabling embedding-guided structural pruning while preserving correctness through exact symbolic verification. By coupling continuous structural abstraction with deterministic matching in a filter–verify pipeline, RGRS effectively reduces the combinatorial search space without compromising logical semantics. Extensive experiments on large-scale knowledge graphs show that RGRS achieves consistently high accuracy with significant efficiency gains over symbolic and neuro-symbolic baselines, providing a principled bridge between symbolic reasoning and embedding-based efficiency.
- 27 October 2024
- Published by Springer Nature
- p. 391-407
Entity Profiling with Graph Rules
- Open Access
- 2 March 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the VLDB Endowment
- Vol. 17 (7) , 1775-1787
Extending Graph Rules with Oracles
This paper proposes a class of graph rules for deducing associations between entities, referred to as Graph Rules with Oracles and denoted by GROs. As opposed to previous graph rules, GROs support ...
- 2 March 2024
- Published by Association for Computing Machinery (ACM) in Proceedings of the VLDB Endowment
- Vol. 17 (7) , 1775-1787
Open AccessExtending Graph Rules with Oracles
This paper proposes a class of graph rules for deducing associations between entities, referred to as Graph Rules with Oracles and denoted by GROs. As opposed to previous graph rules, GROs support ...
- 22 September 2023
- Published by Springer Nature
- p. 352-363
Event Association Analysis Using Graph Rules