Picture for Ruofan Wu

Ruofan Wu

State Space Models on Temporal Graphs: A First-Principles Study

Add code
Jun 03, 2024
Viaarxiv icon

On provable privacy vulnerabilities of graph representations

Add code
Feb 06, 2024
Viaarxiv icon

LasTGL: An Industrial Framework for Large-Scale Temporal Graph Learning

Nov 30, 2023
Figure 1 for LasTGL: An Industrial Framework for Large-Scale Temporal Graph Learning
Figure 2 for LasTGL: An Industrial Framework for Large-Scale Temporal Graph Learning
Figure 3 for LasTGL: An Industrial Framework for Large-Scale Temporal Graph Learning
Figure 4 for LasTGL: An Industrial Framework for Large-Scale Temporal Graph Learning
Viaarxiv icon

Mitigating Estimation Errors by Twin TD-Regularized Actor and Critic for Deep Reinforcement Learning

Add code
Nov 07, 2023
Viaarxiv icon

Privacy-preserving design of graph neural networks with applications to vertical federated learning

Add code
Oct 31, 2023
Figure 1 for Privacy-preserving design of graph neural networks with applications to vertical federated learning
Figure 2 for Privacy-preserving design of graph neural networks with applications to vertical federated learning
Figure 3 for Privacy-preserving design of graph neural networks with applications to vertical federated learning
Figure 4 for Privacy-preserving design of graph neural networks with applications to vertical federated learning
Viaarxiv icon

Hetero$^2$Net: Heterophily-aware Representation Learning on Heterogenerous Graphs

Oct 18, 2023
Figure 1 for Hetero$^2$Net: Heterophily-aware Representation Learning on Heterogenerous Graphs
Figure 2 for Hetero$^2$Net: Heterophily-aware Representation Learning on Heterogenerous Graphs
Figure 3 for Hetero$^2$Net: Heterophily-aware Representation Learning on Heterogenerous Graphs
Figure 4 for Hetero$^2$Net: Heterophily-aware Representation Learning on Heterogenerous Graphs
Viaarxiv icon

Self-supervision meets kernel graph neural models: From architecture to augmentations

Oct 17, 2023
Figure 1 for Self-supervision meets kernel graph neural models: From architecture to augmentations
Figure 2 for Self-supervision meets kernel graph neural models: From architecture to augmentations
Figure 3 for Self-supervision meets kernel graph neural models: From architecture to augmentations
Figure 4 for Self-supervision meets kernel graph neural models: From architecture to augmentations
Viaarxiv icon

FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks

Sep 21, 2023
Figure 1 for FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks
Figure 2 for FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks
Figure 3 for FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks
Figure 4 for FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks
Viaarxiv icon

Scaling Up, Scaling Deep: Blockwise Graph Contrastive Learning

Add code
Jun 03, 2023
Figure 1 for Scaling Up, Scaling Deep: Blockwise Graph Contrastive Learning
Figure 2 for Scaling Up, Scaling Deep: Blockwise Graph Contrastive Learning
Figure 3 for Scaling Up, Scaling Deep: Blockwise Graph Contrastive Learning
Figure 4 for Scaling Up, Scaling Deep: Blockwise Graph Contrastive Learning
Viaarxiv icon

A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks

Add code
May 30, 2023
Figure 1 for A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
Figure 2 for A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
Figure 3 for A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
Figure 4 for A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
Viaarxiv icon