# InstantEmbedding: Efficient Local Node Representations

arXiv: https://arxiv.org/abs/2010.06992 · HTML: https://mlsanity.com/paper/2010.06992/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [Relational Graph Transformer](https://mlsanity.com/paper/2505.10960/) (2025)
- [Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank](https://mlsanity.com/paper/2207.06944/) (2022)
- [Faster Local Solvers for Graph Diffusion Equations](https://mlsanity.com/paper/2410.21634/) (2024)
- [HUGE: Huge Unsupervised Graph Embeddings with TPUs](https://mlsanity.com/paper/2307.14490/) (2023)
- [Fast and Robust Contextual Node Representation Learning over Dynamic Graphs](https://mlsanity.com/paper/2411.07123/) (2024)
- [QUINT: Node embedding using network hashing](https://mlsanity.com/paper/2109.04206/) (2021)
- [A flexible PageRank-based graph embedding framework closely related to spectral eigenvector embeddings](https://mlsanity.com/paper/2207.11321/) (2022)
- [OpenMSD: Towards Multilingual Scientific Documents Similarity Measurement](https://mlsanity.com/paper/2309.10539/) (2023)
- [Analyzing the Evolution of Graphs and Texts](https://mlsanity.com/paper/2411.06295/) (2024)

## Abstract (arXiv)

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.