Spatio temporal gated recurrent unit
AssigneeNEC Laboratories America, Inc.
InventorsWei Cheng, Haifeng Chen, Dongkuan Xu
Life of this patent
Estimating the term…
Abstract
Systems and methods for implementing a spatial and temporal attention-based gated recurrent unit (GRU) for node classification over temporal attributed graphs are provided. The method includes computing, using a GRU, embeddings of nodes at different snapshots. The method includes performing weighted sum pooling of neighborhood nodes for each node. The method further includes concatenating feature vectors for each node. Final temporal network embedding vectors are generated based on the feature vectors for each node. The method also includes applying a classification model based on the final temporal network embedding vectors to the plurality of nodes to determine temporal attributed graphs with classified nodes.
Claims20
A method for implementing a spatial and temporal attention-based gated recurrent unit (GRU) for node classification over temporal attributed graphs, comprising:
- computing, using a gated recurrent unit (GRU), embeddings of each of a plurality of nodes at different snapshots;
- performing weighted sum pooling of neighborhood nodes for each node;
- concatenating feature vectors for each node;
- generating final temporal network embedding vectors based on the feature vectors for each node;
- and
- applying a classification model based on the final temporal network embedding vectors to the plurality of nodes to determine at least one temporal attributed graph with classified nodes.
A computer system for implementing a spatial and temporal attention-based gated recurrent unit (GRU) for node classification over temporal attributed graphs, comprising:
- a processor device operatively coupled to a memory device, the processor device being configured to:
- compute, using a gated recurrent unit (GRU), embeddings of each of a plurality of nodes at different snapshots;
- perform weighted sum pooling of neighborhood nodes for each node;
- concatenate feature vectors for each node;
- generate final temporal network embedding vectors based on the feature vectors for each node;
- and
- apply a classification model based on the final temporal network embedding vectors to the plurality of nodes to determine at least one temporal attributed graph.
A computer program product for implementing a spatial and temporal attention-based gated recurrent unit (GRU) for node classification over temporal attributed graphs, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computing device to cause the computing device to perform the method comprising:
- computing, using a gated recurrent unit (GRU), embeddings of each of a plurality of nodes at different snapshots;
- performing weighted sum pooling of neighborhood nodes for each node;
- concatenating feature vectors for each node;
- generating final temporal network embedding vectors based on the feature vectors for each node;
- and
- applying a classification model based on the final temporal network embedding vectors to the plurality of nodes to determine at least one temporal attributed graph with classified nodes.
Dependencies are inferred from the claim text.