Graph machine learning in the era of large language models (llms)

W Fan, S Wang, J Huang, Z Chen, Y Song… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Graphs play an important role in representing complex relationships in various domains like
social networks, knowledge graphs, and molecular discovery. With the advent of deep …

Generalized graph prompt: Toward a unification of pre-training and downstream tasks on graphs

X Yu, Z Liu, Y Fang, Z Liu, S Chen… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Graphs can model complex relationships between objects, enabling a myriad of Web
applications such as online page/article classification and social recommendation. While …

[HTML][HTML] A Survey of Information Dissemination Model, Datasets, and Insight

Y Liu, P Zhang, L Shi, J Gong - Mathematics, 2023‏ - mdpi.com
Information dissemination refers to how information spreads among users on social
networks. With the widespread application of mobile communication and internet …

Grass: learning spatial–temporal properties from chainlike cascade data for microscopic diffusion prediction

H Li, C **a, T Wang, Z Wang, P Cui… - IEEE Transactions on …, 2023‏ - ieeexplore.ieee.org
Information diffusion prediction captures diffusion dynamics of online messages in social
networks. Thus, it is the basis of many essential tasks such as popularity prediction and viral …

Retrieval-augmented hypergraph for multimodal social media popularity prediction

Z Cheng, J Zhang, X Xu, G Trajcevski, T Zhong… - Proceedings of the 30th …, 2024‏ - dl.acm.org
Accurately predicting the popularity of multimodal user-generated content (UGC) is
fundamental for many real-world applications such as online advertising and …

Counterfactual data augmentation with denoising diffusion for graph anomaly detection

C **ao, S Pang, X Xu, X Li… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
A critical aspect of graph neural networks (GNNs) is to enhance the node representations by
aggregating node neighborhood information. However, when detecting anomalies, the …

Transformer-enhanced Hawkes process with decoupling training for information cascade prediction

L Yu, X Xu, G Trajcevski, F Zhou - Knowledge-Based Systems, 2022‏ - Elsevier
The ability to model the information diffusion process and predict its size is crucial to
understanding information propagation mechanism and is useful for many applications such …

Measuring and classifying IP usage scenarios: a continuous neural trees approach

Z Li, F Zhou, Z Wang, X Xu, L Liu, G Yin - Scientific Reports, 2024‏ - nature.com
Understanding user behavior via IP addresses is a crucial measure towards numerous
pragmatic IP-based applications, including online content delivery, fraud prevention …

A teacher-free graph knowledge distillation framework with dual self-distillation

L Wu, H Lin, Z Gao, G Zhao, SZ Li - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Recent years have witnessed great success in handling graph-related tasks with Graph
Neural Networks (GNNs). Despite their great academic success, Multi-Layer Perceptrons …

PGSL: A probabilistic graph diffusion model for source localization

X Xu, T Qian, Z **ao, N Zhang, J Wu, F Zhou - Expert Systems with …, 2024‏ - Elsevier
Source localization, as a reverse problem of the graph diffusion, bears paramount
significance for a multitude of applications, such as tracking social rumors, detecting …