Mining Expressive Rules in Knowledge Graphs

Ahmadi, Naser; Huynh, Viet-Phi; Meduri, Vamsi; Ortona, Stefano; Papotti, Paolo

doi:10.1145/3371315

Cited by 16 publications

(17 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, they can only identify meta-paths that describe two nodes' similarities instead of generating meta-path for individual nodes to learn their representations for node-wise tasks. Moreover, some work (Tanon et al 2018;Ahmadi et al 2020) concerns the discovery of frequent patterns in a HIN and the subsequent transformation of these patterns into rules, aka rule mining. But the found patterns are not designed for specific tasks or nodes.…”

Section: Related Workmentioning

confidence: 99%

Personalised meta-path generation for heterogeneous graph neural networks

Zhong

Pang

2022

Data Min Knowl Disc

View full text Add to dashboard Cite

Recently, increasing attention has been paid to heterogeneous graph representation learning (HGRL), which aims to embed rich structural and semantic information in heterogeneous information networks (HINs) into low-dimensional node representations. To date, most HGRL models rely on hand-crafted meta-paths. However, the dependency on manually-defined meta-paths requires domain knowledge, which is difficult to obtain for complex HINs. More importantly, the pre-defined or generated meta-paths of all existing HGRL methods attached to each node type or node pair cannot be personalised to each individual node. To fully unleash the power of HGRL, we present a novel framework, Personalised Meta-path based Heterogeneous Graph Neural Networks (PM-HGNN), to jointly generate meta-paths that are personalised for each individual node in a HIN and learn node representations for the target downstream task like node classification. Precisely, PM-HGNN treats the meta-path generation as a Markov Decision Process and utilises a policy network to adaptively generate a meta-path for each individual node and simultaneously learn effective node representations. The policy network is trained with deep reinforcement learning by exploiting the performance improvement on a downstream task. We further propose an extension, PM-HGNN++, to better encode relational structure and accelerate the training during the meta-path generation. Experimental results reveal that both PM-HGNN and PM-HGNN++ can significantly and consistently outperform 16 competing baselines and state-of-the-art methods in various settings of node classification. Qualitative analysis also shows that PM-HGNN++ can identify meaningful meta-paths overlooked by human knowledge.

show abstract

Section: Related Workmentioning

confidence: 99%

Personalised meta-path generation for heterogeneous graph neural networks

Zhong

Pang

2022

Data Min Knowl Disc

View full text Add to dashboard Cite

show abstract

“…The datasets, the code and all the resources used in our work are publicly available through our GitHub repository. 1 Outline. The paper is organized as follows.…”

Section: Introductionmentioning

confidence: 99%

Knowledge Graph Embedding for Link Prediction

Rossi

Barbosa

Firmani

et al. 2021

ACM Trans. Knowl. Discov. Data

380

204

View full text Add to dashboard Cite

Knowledge Graphs (KGs) have found many applications in industrial and in academic settings, which in turn, have motivated considerable research efforts towards large-scale information extraction from a variety of sources. Despite such efforts, it is well known that even the largest KGs suffer from incompleteness; Link Prediction (LP) techniques address this issue by identifying missing facts among entities already in the KG. Among the recent LP techniques, those based on KG embeddings have achieved very promising performance in some benchmarks. Despite the fast-growing literature on the subject, insufficient attention has been paid to the effect of the design choices in those methods. Moreover, the standard practice in this area is to report accuracy by aggregating over a large number of test facts in which some entities are vastly more represented than others; this allows LP methods to exhibit good results by just attending to structural properties that include such entities, while ignoring the remaining majority of the KG. This analysis provides a comprehensive comparison of embedding-based LP methods, extending the dimensions of analysis beyond what is commonly available in the literature. We experimentally compare the effectiveness and efficiency of 18 state-of-the-art methods, consider a rule-based baseline, and report detailed analysis over the most popular benchmarks in the literature.

show abstract

“…Compared to methods purely based on deep neural networks, logic rules are human-comprehensible knowledge and naturally offer explainability of reasoning. Several scalable rule learners have been proposed, including (Galárraga et al 2015;Chen, Wang, and Goldberg 2016b;Yang, Yang, and Cohen 2017;Omran, Wang, and Wang 2018;Meilicke et al 2019;Ahmadi et al 2020;Pirrò 2020), and the learned rules have been successfully applied to link prediction and demonstrated competitive performance (Meilicke et al 2019;Pirrò 2020).…”

Section: Introductionmentioning

confidence: 99%

Learning Typed Rules over Knowledge Graphs

Wang

et al. 2022

Proceedings of the Nineteenth International Conference on Principles of Knowledge Representation and Reasoning

View full text Add to dashboard Cite

Rule learning from large datasets has regained extensive interest as rules are useful for developing explainable approaches to many applications in knowledge graphs. However, existing methods for rule learning are still limited in terms of scalability and rule quality. This paper presents a new method for learning typed rules by employing entity class information. Our experimental evaluation shows the superiority of our system compared to state-of-the-art rule learners. In particular, we demonstrate the usefulness of typed rules in reasoning for link prediction.

show abstract

Mining Expressive Rules in Knowledge Graphs

Cited by 16 publications

References 41 publications

Personalised meta-path generation for heterogeneous graph neural networks

Personalised meta-path generation for heterogeneous graph neural networks

Knowledge Graph Embedding for Link Prediction

Learning Typed Rules over Knowledge Graphs

Contact Info

Product

Resources

About