Robust recommender system: a survey and future directions

K Zhang, Q Cao, F Sun, Y Wu, S Tao, H Shen… - arXiv preprint arXiv …, 2023 - arxiv.org
With the rapid growth of information, recommender systems have become integral for
providing personalized suggestions and overcoming information overload. However, their …

Federated Learning For Heterogeneous Electronic Health Records Utilising Augmented Temporal Graph Attention Networks

S Molaei, A Thakur, G Niknam… - International …, 2024 - proceedings.mlr.press
The proliferation of decentralised electronic healthcare records (EHRs) across medical
institutions requires innovative federated learning strategies for collaborative data analysis …

Repeat-Aware Neighbor Sampling for Dynamic Graph Learning

T Zou, Y Mao, J Ye, B Du - Proceedings of the 30th ACM SIGKDD …, 2024 - dl.acm.org
Dynamic graph learning equips the edges with time attributes and allows multiple links
between two nodes, which is a crucial technology for understanding evolving data scenarios …

Representation Learning of Temporal Graphs with Structural Roles

H Du, L Shi, X Chen, Y Zhao, H Zhang, C Yang… - Proceedings of the 30th …, 2024 - dl.acm.org
Temporal graph representation learning has drawn considerable attention in recent years.
Most existing works mainly focus on modeling local structural dependencies of temporal …

DTFormer: A Transformer-Based Method for Discrete-Time Dynamic Graph Representation Learning

X Chen, Y Xiong, S Zhang, J Zhang, Y Zhang… - Proceedings of the 33rd …, 2024 - dl.acm.org
Discrete-Time Dynamic Graphs (DTDGs), which are prevalent in real-world implementations
and notable for their ease of data acquisition, have garnered considerable attention from …

[HTML][HTML] Dynamic Graph Representation Learning for Passenger Behavior Prediction

M Xie, T Zou, J Ye, B Du, R Huang - Future Internet, 2024 - mdpi.com
Passenger behavior prediction aims to track passenger travel patterns through historical
boarding and alighting data, enabling the analysis of urban station passenger flow and …

Predicting Scientific Impact Through Diffusion, Conformity, and Contribution Disentanglement

Z Xue, G He, Z Jiang, S Gu, Y Kang, S Zhao… - Proceedings of the 33rd …, 2024 - dl.acm.org
The scientific impact of academic papers is influenced by intricate factors such as dynamic
popularity and inherent contribution. Existing models typically rely on static graphs for …

Input Snapshots Fusion for Scalable Discrete Dynamic Graph Nerual Networks

QG Qi, H Chen, M Cheng, H Liu - arXiv preprint arXiv:2405.06975, 2024 - arxiv.org
Dynamic graphs are ubiquitous in the real world, yet there is a lack of suitable theoretical
frameworks to effectively extend existing static graph models into the temporal domain …

Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding

Z Wang, S Zhou, J Chen, Z Zhang, B Hu, Y Feng… - arXiv preprint arXiv …, 2024 - arxiv.org
Learning effective representations for Continuous-Time Dynamic Graphs (CTDGs) has
garnered significant research interest, largely due to its powerful capabilities in modeling …

Disentangled Hyperbolic Representation Learning for Heterogeneous Graphs

Q Bai, C Nie, H Zhang, Z Dou, X Yuan - arXiv preprint arXiv:2406.10367, 2024 - arxiv.org
Heterogeneous graphs have attracted a lot of research interests recently due to the success
for representing complex real-world systems. However, existing methods have two pain …