Reinforcement learning based meta-path discovery in large-scale heterogeneous information networks

G Wan, B Du, S Pan, G Haffari - Proceedings of the aaai conference on …, 2020 - ojs.aaai.org
Meta-paths are important tools for a wide variety of data mining and network analysis tasks
in Heterogeneous Information Networks (HINs), due to their flexibility and interpretability to …

Mutual information model for link prediction in heterogeneous complex networks

H Shakibian, N Moghadam Charkari - Scientific reports, 2017 - nature.com
Recently, a number of meta-path based similarity indices like PathSim, HeteSim, and
random walk have been proposed for link prediction in heterogeneous complex networks …

Automatic meta-path discovery for effective graph-based recommendation

W Ning, R Cheng, J Shen, NAH Haldar, B Kao… - Proceedings of the 31st …, 2022 - dl.acm.org
Heterogeneous Information Networks (HINs) are labeled graphs that depict relationships
among different types of entities (eg, users, movies and directors). For HINs, meta-path …

Meta-Path Learning for Multi-relational Graph Neural Networks

F Ferrini, A Longa, A Passerini… - Learning on Graphs …, 2024 - proceedings.mlr.press
Existing multi-relational graph neural networks use one of two strategies for identifying
informative relations: either they reduce this problem to low-level weight learning, or they …

A multilayered approach for link prediction in heterogeneous complex networks

H Shakibian, NM Charkari, S Jalili - Journal of Computational Science, 2016 - Elsevier
Link prediction problem is a difficult task in complex networks due to (i) network size and
sparsity, and (ii) extracting efficient similarity measures between node pairs. Although many …

Multi-kernel one class link prediction in heterogeneous complex networks

H Shakibian, NM Charkari, S Jalili - Applied Intelligence, 2018 - Springer
The heterogeneity of a network causes major challenges for link prediction in
heterogeneous complex networks. To deal with this problem, supervised link prediction …

Evaluating top-k meta path queries on large heterogeneous information networks

Z Zhu, R Cheng, L Do, Z Huang… - 2018 IEEE International …, 2018 - ieeexplore.ieee.org
Heterogeneous information networks (HINs), which are typed graphs with labeled nodes
and edges, have attracted tremendous interest from academia and industry. Given two HIN …

Reinforced meta-path selection for recommendation on heterogeneous information networks

W Ning, R Cheng, J Shen, NAH Haldar, B Kao… - 2021 - research-repository.uwa.edu.au
Abstract Heterogeneous Information Networks (HINs) capture complex relations among
entities of various kinds and have been used extensively to improve the effectiveness of …

MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks

Z Liu, K Duan, J Yang, H Xu, M Zhang… - arxiv preprint arxiv …, 2022 - arxiv.org
Heterogeneous Information Network (HIN) is essential to study complicated networks
containing multiple edge types and node types. Meta-path, a sequence of node types and …

LLM4HIN: Discovering Meta-path with Large Language Model for Reasoning on Complex Heterogeneous Information Networks

H Cheng, S Liu, C Fan, K Huang, H He… - … on Internet of Things …, 2024 - ieeexplore.ieee.org
Heterogeneous Information Networks (HINs) are complex structures hosting various types of
entity nodes and diverse relationships. Meta-paths are crucial in HINs for relaying detailed …