# Creating generalizable downstream graph models with random projections

arXiv: https://arxiv.org/abs/2302.08895 · HTML: https://mlsanity.com/paper/2302.08895/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 17 Feb 2023.

## Builds on (most cited first, 10 of 10)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [The Surprising Power of Graph Neural Networks with Random Node Initialization](https://mlsanity.com/paper/2010.01179/) (2020)
- [Random Features Strengthen Graph Neural Networks](https://mlsanity.com/paper/2002.03155/) (2020)
- [On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs](https://mlsanity.com/paper/2107.01495/) (2021)
- [Fast and Accurate Network Embeddings via Very Sparse Random Projection](https://mlsanity.com/paper/1908.11512/) (2019)
- [Billion-scale Network Embedding with Iterative Random Projection](https://mlsanity.com/paper/1805.02396/) (2018)
- [On Node Features for Graph Neural Networks](https://mlsanity.com/paper/1911.08795/) (2019)

## Built on by (most cited first, 1 of 1)

- [Node Similarities under Random Projections: Limits and Pathological Cases](https://mlsanity.com/paper/2404.10148/) (2024)

## Abstract (arXiv)

We investigate graph representation learning approaches that enable models to generalize across graphs: given a model trained using the representations from one graph, our goal is to apply inference using those same model parameters when given representations computed over a new graph, unseen during model training, with minimal degradation in inference accuracy. This is in contrast to the more common task of doing inference on the unseen nodes of the same graph. We show that using random projections to estimate multiple powers of the transition matrix allows us to build a set of isomorphism-invariant features that can be used by a variety of tasks. The resulting features can be used to recover enough information about the local neighborhood of a node to enable inference with relevance competitive to other approaches while maintaining computational efficiency.