Year: 2020
Type: preprint
Abstract: In this paper, we introduce InstantEmbedding, an efficient method for generating single-node representations using local PageRank computations. We theoretically prove that our approach produces globally consistent representations in sublinear time. We demonstrate this empirically by conducting extensive experiments on real-world datasets with over a billion edges. Our experiments confirm that InstantEmbedding requires drastically less computation time (over 9,000 times faster) and less memory (by over 8,000 times) to produce a single node's embedding than traditional methods including DeepWalk, node2vec, VERSE, and FastRP. We also show that our method produces high quality representations, demonstrating results that meet or exceed the state of the art for unsupervised representation learning on tasks like node classification and link prediction.
Source: arXiv (Cornell University)
Authors: Postăvaru, Ştefan, Tsitsulin, Anton, de Almeida, Filipe Miguel Gonçalves, Tian, Yingtao, Lattanzi, Silvio, Perozzi, Bryan
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W3093333044