Spread-gram: A spreading-activation schema of network structural learning
This work addresses network representation learning for tasks like semantic and protein interaction analysis, offering a novel approach that is incremental in improving existing methods.
The paper tackles the problem of information bias and sparsity in network representation learning by proposing a method inspired by human memory, which learns node embeddings through network spreading structures, resulting in significant improvements across various real-world networks and efficient training with linear time complexity.
Network representation learning has exploded recently. However, existing studies usually reconstruct networks as sequences or matrices, which may cause information bias or sparsity problem during model training. Inspired by a cognitive model of human memory, we propose a network representation learning scheme. In this scheme, we learn node embeddings by adjusting the proximity of nodes traversing the spreading structure of the network. Our proposed method shows a significant improvement in multiple analysis tasks based on various real-world networks, ranging from semantic networks to protein interaction networks, international trade networks, human behavior networks, etc. In particular, our model can effectively discover the hierarchical structures in networks. The well-organized model training speeds up the convergence to only a small number of iterations, and the training time is linear with respect to the edge numbers.