Associative Learning for Network Embedding
This work addresses network embedding for researchers and practitioners, but it is incremental as it builds on existing techniques with a new perspective.
The authors tackled the network embedding problem by proposing a method that uses Modern Hopfield Networks for associative learning, achieving competitive performance in node classification and linkage prediction tasks.
The network embedding task is to represent the node in the network as a low-dimensional vector while incorporating the topological and structural information. Most existing approaches solve this problem by factorizing a proximity matrix, either directly or implicitly. In this work, we introduce a network embedding method from a new perspective, which leverages Modern Hopfield Networks (MHN) for associative learning. Our network learns associations between the content of each node and that node's neighbors. These associations serve as memories in the MHN. The recurrent dynamics of the network make it possible to recover the masked node, given that node's neighbors. Our proposed method is evaluated on different downstream tasks such as node classification and linkage prediction. The results show competitive performance compared to the common matrix factorization techniques and deep learning based methods.