InstantEmbedding: Efficient Local Node Representations

Stefan Postavaru, Anton Tsitsulin, Filipe Miguel Goncalves de Almeida, Yingtao Tian, Silvio Lattanzi, Bryan Perozzi

Keywords: Node Embedding, Structural Graph Representations, Graph Embedding, Local Algorithms

Abstract: In this paper, we introduce InstantEmbedding, an efficient method for generating single-node representations using local PageRank computations. We 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.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: Embed nodes using only local graph information, in sublinear time and space.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2010.06992/code)

Reviewed Version (pdf): https://openreview.net/references/pdf?id=VOUUgH9Nht