RECORD
Ruleformer: Context-aware Differentiable Rule Mining over Knowledge Graph
Logic in Computer Science · Submitted 13 Sep 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim The experiment results show the necessity of considering these information in rule mining task and the effectiveness of our model.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Rule mining is an effective approach for reasoning over knowledge graph (KG). Existing works mainly concentrate on mining rules. However, there might be several rules that could be applied for reasoning for one relation, and how to select appropriate rules for completion of different triples has not been discussed. In this paper, we propose to take the context information into consideration, which helps select suitable rules for the inference tasks. Based on this idea, we propose a transformer-based rule mining approach, Ruleformer. It consists of two blocks: 1) an encoder extracting the context information from subgraph of head entities with modified attention mechanism, and 2) a decoder which aggregates the subgraph information from the encoder output and generates the probability of relations for each step of reasoning. The basic idea behind Ruleformer is regarding rule mining process as a sequence to sequence task. To make the subgraph a sequence input to the encoder and retain the graph structure, we devise a relational attention mechanism in Transformer. The experiment results show the necessity of considering these information in rule mining task and the effectiveness of our model.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Rule mining is an effective approach for reasoning over knowledge graph (KG). | background 1.00 | 0.05 | 0.03 | asserted 1.00 |
| s1 | Existing works mainly concentrate on mining rules. | background 0.98 | 0.03 | 0.02 | asserted 1.00 |
| s2 | However, there might be several rules that could be applied for reasoning for one relation, and how to select appropriate rules for completion of different triples has not been discussed. | gap 1.00 | 0.06 | 0.04 | speculative 0.60 |
| s3 | In this paper, we propose to take the context information into consideration, which helps select suitable rules for the inference tasks. | contribution 0.94 | 0.39 | 0.15 | asserted 0.88 |
| s4 | Based on this idea, we propose a transformer-based rule mining approach, Ruleformer. | contribution 0.89 | 0.89 | 0.08 | asserted 1.00 |
| s5 | It consists of two blocks: 1) an encoder extracting the context information from subgraph of head entities with modified attention mechanism, and 2) a decoder which aggregates the subgraph information from the encoder output and generates the probability of relations for each step of reasoning. | method 1.00 | 0.86 | 0.07 | asserted 1.00 |
| s6 | The basic idea behind Ruleformer is regarding rule mining process as a sequence to sequence task. | method 0.94 | 0.56 | 0.05 | asserted 1.00 |
| s7 | To make the subgraph a sequence input to the encoder and retain the graph structure, we devise a relational attention mechanism in Transformer. | method 0.97 | 0.92 | 0.04 | asserted 0.99 |
| s8 | The experiment results show the necessity of considering these information in rule mining task and the effectiveness of our model. | result 0.90 | 0.95 | 0.70 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Rule mining is an effective approach for reasoning over knowledge graph (KG). Existing works mainly concentrate on mining rules. However, there might be several rules that could be applied for reasoning for one relation, and how to select appropriate rules for completion of different triples has not been discussed. In this paper, we propose to take the context information into consideration, which helps select suitable rules for the inference tasks. Based on this idea, we propose a transformer-based rule mining approach, Ruleformer. It consists of two blocks: 1) an encoder extracting the context information from subgraph of head entities with modified attention mechanism, and 2) a decoder which aggregates the subgraph information from the encoder output and generates the probability of relations for each step of reasoning. The basic idea behind Ruleformer is regarding rule mining process as a sequence to sequence task. To make the subgraph a sequence input to the encoder and retain the graph structure, we devise a relational attention mechanism in Transformer. The experiment results show the necessity of considering these information in rule mining task and the effectiveness of our model.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites
Cites as background 1 paper
-
More recently, differentiable rule learning methods based on TensorLog [ref] are proposed, which can learn the confidence and structure of rule at the same time.
TensorLog: A Differentiable Deductive Database · Rule Learning Methods · 0.82
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.