iN2V: Bringing Transductive Node Embeddings to Inductive Graphs
This addresses the problem of applying node embeddings to new nodes in graphs for researchers and practitioners, but it is incremental as it builds on existing transductive methods.
The paper tackles the limitation of transductive node embeddings like node2vec by proposing iN2V, an inductive method that computes embeddings for unseen nodes, improving node classification by an average of 1 point with up to 6 points on benchmark datasets.
Shallow node embeddings like node2vec (N2V) can be used for nodes without features or to supplement existing features with structure-based information. Embedding methods like N2V are limited in their application on new nodes, which restricts them to the transductive setting where the entire graph, including the test nodes, is available during training. We propose inductive node2vec (iN2V), which combines a post-hoc procedure to compute embeddings for nodes unseen during training and modifications to the original N2V training procedure to prepare the embeddings for this post-hoc procedure. We conduct experiments on several benchmark datasets and demonstrate that iN2V is an effective approach to bringing transductive embeddings to an inductive setting. Using iN2V embeddings improves node classification by 1 point on average, with up to 6 points of improvement depending on the dataset and the number of unseen nodes. Our iN2V is a plug-in approach to create new or enrich existing embeddings. It can also be combined with other embedding methods, making it a versatile approach for inductive node representation learning. Code to reproduce the results is available at https://github.com/Foisunt/iN2V .