GPSP: Graph Partition and Space Projection based Approach for Heterogeneous Network Embedding
This work addresses the challenge of heterogeneous network embedding for network mining applications, representing an incremental advancement in the field.
The paper tackles the problem of learning representations for heterogeneous networks with multiple node and link types by proposing GPSP, which partitions the network into homogeneous and bipartite subnetworks and learns projective embeddings, resulting in improved performance over state-of-the-art baselines in node classification and clustering tasks on a real-life dataset.
In this paper, we propose GPSP, a novel Graph Partition and Space Projection based approach, to learn the representation of a heterogeneous network that consists of multiple types of nodes and links. Concretely, we first partition the heterogeneous network into homogeneous and bipartite subnetworks. Then, the projective relations hidden in bipartite subnetworks are extracted by learning the projective embedding vectors. Finally, we concatenate the projective vectors from bipartite subnetworks with the ones learned from homogeneous subnetworks to form the final representation of the heterogeneous network. Extensive experiments are conducted on a real-life dataset. The results demonstrate that GPSP outperforms the state-of-the-art baselines in two key network mining tasks: node classification and clustering.