Temporal Graph Neural Network
A neural network model for dynamic graph learning tasks that updates node memories from evolving interaction events and uses the memories for downstream prediction.
Timeline (last 90 days)
Temporal graph neural networks (TGNNs) update node memories from evolving interactions (events) and use these memories for downstream prediction.
In TGNNs, each event updates node memories, and subsequent events depend on the memories updated by preceding events, making training difficult to parallelize.
In TGNN training, a root event is an event selected as the prediction target, and the model needs to predict the occurrence of that event based on the node memories preceding it; support events are historical events sampled backward to predict the root event, providing context and participating in node memory updates.
Node memory is one of the core components of TGNNs, usually a vector indexed by node, used to summarize the historical interaction information of that node up to the current moment.
All Facts (4)
Temporal graph neural networks (TGNNs) update node memories from evolving interactions (events) and use these memories for downstream prediction.
50%UnverifiedIn TGNNs, each event updates node memories, and subsequent events depend on the memories updated by preceding events, making training difficult to parallelize.
50%UnverifiedIn TGNN training, a root event is an event selected as the prediction target, and the model needs to predict the occurrence of that event based on the node memories preceding it; support events are historical events sampled backward to predict the root event, providing context and participating in node memory updates.
50%UnverifiedNode memory is one of the core components of TGNNs, usually a vector indexed by node, used to summarize the historical interaction information of that node up to the current moment.
50%