A Symbolic Rule Integration Framework with Logic Transformer for Inductive Relation Prediction
Open Access
- 13 May 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2181-2192
Abstract
Relation prediction in knowledge graphs (KGs) aims at predicting missing relations in incomplete triples, whereas the dominant paradigm by KG embeddings has a limitation to predict the relation between unseen entities. This situation is called an inductive setting, which is more common in the real-world scenario. To handle this issue, implicit symbolic rules have shown great potential in capturing the inductive capability. However, it is still challenging to obtain precise representations of logic rules from KGs. The argument variability and predicate non-commutativity in symbolic rule integration make the modeling of component symbols difficult. To this end, we propose a novel inductive relation prediction model named SymRITa with a logic transformer integrating rules. SymRITa firstly extracts the subgraph, whose embeddings are captured by a graph network. Meanwhile, symbolic rule graphs in the subgraph can be generated. Then, the symbolic rules are modeled by a proposed logic transformer. Specifically, the input format based on the subgraph-based embeddings is to focus on the argument variability in symbolic rules. In addition, a conjunction attention mechanism in the logic transformer can resolve predicate non-commutativity in the symbolic rule integration process. Finally, the subgraph-based and symbol-based embeddings obtained from the previous steps are combined for the training regime, and prediction results as well as rules explaining the reasoning process are explicitly output. Extensive experiments on twelve inductive datasets show that SymRITa achieves outstanding effectiveness compared to state-of-the-art inductive baselines. Moreover, the logic rules with corresponding confidences provide an interpretable paradigm.Keywords
Funding Information
- National Natural Science Foundation of China (62137002, 62293550, 62293553, 62293554, 62176207, 62106190, 62192781, and 62250009)
- The Youth Innovation Team of Shaanxi Universities
- the Minister of Education, Singapore (T2EP20120-0019, MOET32020-0004)
- ?LENOVO-XJTU Intelligent Industry Joint Laboratory Project
- XJTU Teaching Reform Research Project Acquisition Learning Based on Knowledge Forest
- National Key Research and Development Program of China (2022YFC3303600)
- Foundation of Key National Defense Science and Technology Laboratory (6142101210201)
- Innovative Research Group of the National Natural Science Foundation of China (61721002)
- Natural Science Basic Research Program of Shaanxi Province (2023-JC-YB-593)
- Project of China Knowledge Centre for Engineering Science and Technology
- National Research Foundation, Singapore, and the Cyber Security Agency under its National Cybersecurity R\&D Programme (NCRP25-P04-TAICeN)
- DSO National Laboratories under the AI Singapore Programme (AISG Award No: AISG2-GC-2023-008)
This publication has 28 references indexed in Scilit:
- Persona Consistent Dialogue Generation via Contrastive Learning2023
- Hierarchy-Aware Multi-Hop Question Answering over Knowledge Graphs2023
- Relational Message Passing for Fully Inductive Knowledge Graph Completion2023
- Logiformer2022
- KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction2022
- Knowledge Graph Reasoning with Relational Digraph2022
- Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion2021
- ConceptNet 5.5: An Open Multilingual Graph of General KnowledgeProceedings of the AAAI Conference on Artificial Intelligence, 2017
- Knowledge Graph Embedding by Translating on HyperplanesProceedings of the AAAI Conference on Artificial Intelligence, 2014
- Inductive logic programmingNew Generation Computing, 1991