Temporal GNN

Temporal Graph Neural Networks (Temporal GNNs) aim to leverage the power of graph neural networks for data with inherent temporal dependencies, improving upon static GNNs by incorporating time-evolving relationships and attributes. Current research focuses on efficiently handling long-term dependencies, developing statistically sound methods for identifying meaningful temporal patterns, and optimizing training and inference for large-scale datasets and real-time applications, often employing memory-based architectures and novel sampling techniques. These advancements are significant for various applications, including fraud detection, brain connectivity prediction, and real-time analysis of dynamic systems, offering improved accuracy and efficiency compared to traditional methods.

Papers

October 21, 2024

Resilient Temporal GCN for Smart Grid State Estimation Under Topology Inaccuracies
Seyed Hamed Haghshenas, Mia Naeini
Graph Neural Network State Estimation Topological Feature Temporal Graph Topology Problem Factual Error Uncertain System Temporal GNN System State Estimation

August 10, 2024

An Information-Theoretic Analysis of Temporal GNNs
Amirmohammad Farzaneh
Information Bottleneck Information Theory Temporal Graph Neural Network Temporal GNN Information Rate

June 24, 2024

Inference of Sequential Patterns for Neural Message Passing in Temporal Graphs
Jan von Pichowski, Vincenzo Perri, Lisi Qarkaxhija, Ingo Scholtes
Scientific Inference Temporal Graph Message Passing Temporal Pattern Sequential Pattern Temporal GNN

April 30, 2024

Active Dendrites Enable Efficient Continual Learning in Time-To-First-Spike Neural Networks
Lorenzo Pes, Rick Luiken, Federico Corradi, Charlotte Frenkel
Neural Network Catastrophic Forgetting Spike Timing Temporal GNN Active Dendrite Pyramidal Neuron

February 23, 2024

MSPipe: Efficient Temporal GNN Training via Staleness-aware Pipeline
Guangming Sheng, Junwei Su, Chao Huang, Chuan Wu
Temporal Dependency Temporal Graph Temporal Graph Neural Network Temporal GNN Static Deep Neural Network

February 14, 2024

Robust Training of Temporal GNNs using Nearest Neighbours based Hard Negatives
Shubham Gupta, Srikanta Bedathur
Link Prediction Nearest Neighbor Temporal Graph Negative Sampling Robust Training Self Supervised Loss Hard Negative Temporal GNN

January 1, 2024

Predicting Infant Brain Connectivity with Federated Multi-Trajectory GNNs using Scarce Data
Michalis Pistos, Gang Li, Weili Lin, Dinggang Shen, Islem Rekik
Federated Prompt Cooperation Scarce Data Temporal GNN Longitudinal Brain

November 29, 2023

GNNFlow: A Distributed Framework for Continuous Temporal GNN Learning on Dynamic Graphs
Yuchen Zhong, Guangming Sheng, Tianzuo Qin, Minjie Wang, Quan Gan, Chuan Wu
Graph Neural Network New Framework Dynamic Graph Deep Graph Temporal GNN Temporal Graph Representation Learning

July 19, 2023

TUNeS: A Temporal U-Net with Self-Attention for Video-based Surgical Phase Recognition
Isabel Funke, Dominik Rivoir, Stefanie Krell, Stefanie Speidel
Self Attention Attention Mechanism LSTM Network Surgical Phase Recognition Temporal GNN

February 2, 2023

Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities
Antonio Longa, Veronica Lachi, Gabriele Santin, Monica Bianchini, Bruno Lepri, Pietro Lio, Franco Scarselli, Andrea Passerini
Graph Neural Network Graph Drawing Emerging Opportunity Internal State Temporal Graph Open Challenge Temporal GNN

November 22, 2022

Motif-aware temporal GCN for fraud detection in signed cryptocurrency trust networks
Song Li, Jiandong Zhou, Chong MO, Jin LI, Geoffrey K. F. Tso, Yuxing Tian
Fraud Detection Trust Inference Temporal GNN GNN Aggregation Cryptocurrency Transaction Network

June 12, 2022

tBDFS: Temporal Graph Neural Network Leveraging DFS
Uriel Singer, Haggai Roitman, Ido Guy, Kira Radinsky
Temporal Graph Temporal Graph Neural Network Deep Recurrent Neural Network Temporal GNN Depth First Search Temporal Path

March 28, 2022

TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs
Hongkuan Zhou, Da Zheng, Israt Nisa, Vasileios Ioannidis, Xiang Song, George Karypis
General Framework Temporal Graph Neural Network Temporal GNN Temporal Neighbor Billion Scale Graph

March 10, 2022

Model-Architecture Co-Design for High Performance Temporal GNN Inference on FPGA
Hongkuan Zhou, Bingyi Zhang, Rajgopal Kannan, Viktor Prasanna, Carl Busart
Field Programmable Gate Array Temporal Graph Temporal Graph Neural Network Model Architecture Temporal Embeddings Temporal GNN Temporal Neighbor

March 4, 2022

GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation
Zheng Lian, Lan Chen, Licai Sun, Bin Liu, Jianhua Tao
Multimodal Data Potential Conversation Outcome Conversational Data Dialogue Benchmark Temporal GNN Conversation Understanding Graph Completion

Temporal GNN

Papers

Resilient Temporal GCN for Smart Grid State Estimation Under Topology Inaccuracies

An Information-Theoretic Analysis of Temporal GNNs

Inference of Sequential Patterns for Neural Message Passing in Temporal Graphs

Active Dendrites Enable Efficient Continual Learning in Time-To-First-Spike Neural Networks

MSPipe: Efficient Temporal GNN Training via Staleness-aware Pipeline

Robust Training of Temporal GNNs using Nearest Neighbours based Hard Negatives

Predicting Infant Brain Connectivity with Federated Multi-Trajectory GNNs using Scarce Data

GNNFlow: A Distributed Framework for Continuous Temporal GNN Learning on Dynamic Graphs

TUNeS: A Temporal U-Net with Self-Attention for Video-based Surgical Phase Recognition

Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities

Motif-aware temporal GCN for fraud detection in signed cryptocurrency trust networks

tBDFS: Temporal Graph Neural Network Leveraging DFS

TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs

Model-Architecture Co-Design for High Performance Temporal GNN Inference on FPGA

GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation