# Principled approach to the selection of the embedding dimension of networks

arXiv: https://arxiv.org/abs/2004.09928 · HTML: https://mlsanity.com/paper/2004.09928/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2020.

## Built on by (most cited first, 19 of 19)

- [From Local to Global: Spectral-Inspired Graph Neural Networks](https://mlsanity.com/paper/2209.12054/) (2022)
- [The maximum capability of a topological feature in link prediction](https://mlsanity.com/paper/2206.15101/) (2022)
- [Robustness of shallow graph embedding methods for community detection](https://mlsanity.com/paper/2405.00636/) (2024)
- [How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings](https://mlsanity.com/paper/2503.01723/) (2025)
- [Zoo Guide to Network Embedding](https://mlsanity.com/paper/2305.03474/) (2023)
- [Efficient Network Embedding by Approximate Equitable Partitions](https://mlsanity.com/paper/2409.10160/) (2024)
- [Angular Constraint Embedding via SpherePair Loss for Constrained Clustering](https://mlsanity.com/paper/2510.06907/) (2025)
- [On the Effectiveness of Proposed Techniques to Reduce Energy Consumption in RAG Systems: A Controlled Experiment](https://mlsanity.com/paper/2601.02522/) (2026)
- [ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention](https://mlsanity.com/paper/2305.12121/) (2023)
- [Tabular Learning: Encoding for Entity and Context Embeddings](https://mlsanity.com/paper/2403.19405/) (2024)
- [Detecting Masquerade Attacks in Controller Area Networks Using Graph Machine Learning](https://mlsanity.com/paper/2408.05427/) (2024)
- [Rank Is Not Capacity: Spectral Occupancy for Latent Graph Models](https://mlsanity.com/paper/2605.11142/) (2026)
- [DeepProphet2 -- A Deep Learning Gene Recommendation Engine](https://mlsanity.com/paper/2208.01918/) (2022)
- [Design of the topology for contrastive visual-textual alignment](https://mlsanity.com/paper/2209.02127/) (2022)
- [GeoT: Tensor Centric Library for Graph Neural Network via Efficient Segment Reduction on GPU](https://mlsanity.com/paper/2404.03019/) (2024)
- [Multi-Scale Node Embeddings for Graph Modeling and Generation](https://mlsanity.com/paper/2412.04354/) (2024)
- [Embedding Learning on Multiplex Networks for Link Prediction](https://mlsanity.com/paper/2602.01922/) (2026)
- [The Impact of Dimensionality on the Stability of Node Embeddings](https://mlsanity.com/paper/2604.08492/) (2026)
- [Optimal Allocation of Embedding Dimensions under Finite-Sample Constraints](https://mlsanity.com/paper/2608.24592/) (2026)

## Abstract (arXiv)

Network embedding is a general-purpose machine learning technique that encodes network structure in vector spaces with tunable dimension. Choosing an appropriate embedding dimension -- small enough to be efficient and large enough to be effective -- is challenging but necessary to generate embeddings applicable to a multitude of tasks. Existing strategies for the selection of the embedding dimension rely on performance maximization in downstream tasks. Here, we propose a principled method such that all structural information of a network is parsimoniously encoded. The method is validated on various embedding algorithms and a large corpus of real-world networks. The embedding dimension selected by our method in real-world networks suggest that efficient encoding in low-dimensional spaces is usually possible.