GNN-IR: Examining graph neural networks for influencer recommendations in social media marketing

J Park, H Ahn, D Kim, E Park - Journal of Retailing and Consumer Services, 2024 - Elsevier
With the notable growth of the Internet, a number of platforms have emerged and attracted
an enormous number of users. Based on the impact of these platforms, some 'influencers' …

Node classification oriented Adaptive Multichannel Heterogeneous Graph Neural Network

Y Li, C Jian, G Zang, C Song, X Yuan - Knowledge-Based Systems, 2024 - Elsevier
Heterogeneous graph neural networks (HGNNs) play an important role in accomplishing
node classification on heterogeneous graphs (HGs). These models are built on the …

Few-shot causal representation learning for out-of-distribution generalization on heterogeneous graphs

P Ding, Y Wang, G Liu, N Wang, X Zhou - arXiv preprint arXiv:2401.03597, 2024 - arxiv.org
Heterogeneous graph few-shot learning (HGFL) has been developed to address the label
sparsity issue in heterogeneous graphs (HGs), which consist of various types of nodes and …

Long-range Meta-path Search on Large-scale Heterogeneous Graphs

C Li, Z Guo, Q He, K He - The Thirty-eighth Annual Conference on …, 2024 - openreview.net
Utilizing long-range dependency, a concept extensively studied in homogeneous graphs,
remains underexplored in heterogeneous graphs, especially on large ones, posing two …

Road Network Representation Learning with the Third Law of Geography

H Zhou, W Huang, Y Chen, T He, G Cong… - arXiv preprint arXiv …, 2024 - arxiv.org
Road network representation learning aims to learn compressed and effective vectorized
representations for road segments that are applicable to numerous tasks. In this paper, we …

Type-adaptive graph Transformer for heterogeneous information networks

Y Tang, Y Huang, J Hou, Z Liu - Applied Intelligence, 2024 - Springer
Many real-world applications use diverse types of nodes and edges to retain rich semantic
information. These applications are modeled as heterogeneous graphs. Recent research on …

Observation impact explanation in atmospheric state estimation using hierarchical message-passing graph neural networks

HJ Jeon, J Kang, IH Kwon, OJ Lee - Machine Learning: Science …, 2024 - iopscience.iop.org
The impact of meteorological observations on weather forecasting varies with the sensor
type, location, time, and other environmental factors. Thus, the quantitative analysis of …

Heterogeneous Sheaf Neural Networks

L Braithwaite, I Duta, P Liò - arXiv preprint arXiv:2409.08036, 2024 - arxiv.org
Heterogeneous graphs, with nodes and edges of different types, are commonly used to
model relational structures in many real-world applications. Standard Graph Neural …

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 …

NoiseHGNN: Synthesized Similarity Graph-Based Neural Network For Noised Heterogeneous Graph Representation Learning

X Zhang, C Xie, H Duan, B Yu - arXiv preprint arXiv:2412.18267, 2024 - arxiv.org
Real-world graph data environments intrinsically exist noise (eg, link and structure errors)
that inevitably disturb the effectiveness of graph representation and downstream learning …