Loss-aware curriculum learning for heterogeneous graph neural networks
Heterogeneous Graph Neural Networks (HGNNs) are a class of deep learning models
designed specifically for heterogeneous graphs, which are graphs that contain different …
designed specifically for heterogeneous graphs, which are graphs that contain different …
[HTML][HTML] LHGCN: A Laminated Heterogeneous Graph Convolutional Network for Modeling User–Item Interaction in E-Commerce
K Liu, M Kang, X Li, W Dai - Symmetry, 2024 - mdpi.com
The e-commerce data structure is a typical multiplex graph network structure, which allows
multiple types of edges between node pairs. However, existing methods that rely on …
multiple types of edges between node pairs. However, existing methods that rely on …
Multi-Scale Heterogeneous Text-Attributed Graph Datasets From Diverse Domains
Heterogeneous Text-Attributed Graphs (HTAGs), where different types of entities are not
only associated with texts but also connected by diverse relationships, have gained …
only associated with texts but also connected by diverse relationships, have gained …
Coarse-to-Fine Robust Heterogeneous Network Representation Learning without Metapath
L Chen, H Guo, Y Lei, Y Li, Z Liu - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Influenced by the heterogeneity, representation learning while preserving the structural and
semantic information is more challenging for heterogeneous networks (HNs) than for …
semantic information is more challenging for heterogeneous networks (HNs) than for …
Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach
H Gao, C Zhang, F Wu, J Zhao, C Zheng… - arXiv preprint arXiv …, 2024 - arxiv.org
Graph representation learning methods are highly effective in handling complex non-
Euclidean data by capturing intricate relationships and features within graph structures …
Euclidean data by capturing intricate relationships and features within graph structures …