# A Comparative Study for Unsupervised Network Representation Learning

arXiv: https://arxiv.org/abs/1903.07902 · HTML: https://mlsanity.com/paper/1903.07902/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2019.

## Built on by (most cited first, 16 of 16)

- [GraphWorld: Fake Graphs Bring Real Insights for GNNs](https://mlsanity.com/paper/2203.00112/) (2022)
- [Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks](https://mlsanity.com/paper/2105.08621/) (2021)
- [CitationIE: Leveraging the Citation Graph for Scientific Information Extraction](https://mlsanity.com/paper/2106.01560/) (2021)
- [BAGEL: A Benchmark for Assessing Graph Neural Network Explanations](https://mlsanity.com/paper/2206.13983/) (2022)
- [Alignment and stability of embeddings: measurement and inference improvement](https://mlsanity.com/paper/2101.07251/) (2021)
- [GraphScale: A Framework to Enable Machine Learning over Billion-node Graphs](https://mlsanity.com/paper/2407.15452/) (2024)
- [Impact Of Missing Data Imputation On The Fairness And Accuracy Of Graph Node Classifiers](https://mlsanity.com/paper/2211.00783/) (2022)
- [Free Energy Node Embedding via Generalized Skip-gram with Negative Sampling](https://mlsanity.com/paper/2105.09182/) (2021)
- [Network representation learning systematic review: ancestors and current development state](https://mlsanity.com/paper/2109.07583/) (2021)
- [On the Use of Unrealistic Predictions in Hundreds of Papers Evaluating Graph Representations](https://mlsanity.com/paper/2112.04274/) (2021)
- [Disentangled and Self-Explainable Node Representation Learning](https://mlsanity.com/paper/2410.21043/) (2024)
- [Node Embeddings via Neighbor Embeddings](https://mlsanity.com/paper/2503.23822/) (2025)
- [Semantic Representation Learning of Scientific Literature based on Adaptive Feature and Graph Neural Network](https://mlsanity.com/paper/2311.00296/) (2023)
- [Learning Graph Node Embeddings by Smooth Pair Sampling](https://mlsanity.com/paper/2501.12884/) (2025)
- [Population-Scale Network Embeddings Expose Educational Divides in Network Structure Related to Right-Wing Populist Voting](https://mlsanity.com/paper/2508.21236/) (2025)
- [Manifold-Preserving Superpixel Hierarchies and Embeddings for the Exploration of High-Dimensional Images](https://mlsanity.com/paper/2602.24160/) (2026)

## Abstract (arXiv)

There has been appreciable progress in unsupervised network representation learning (UNRL) approaches over graphs recently with flexible random-walk approaches, new optimization objectives and deep architectures. However, there is no common ground for systematic comparison of embeddings to understand their behavior for different graphs and tasks. In this paper we theoretically group different approaches under a unifying framework and empirically investigate the effectiveness of different network representation methods. In particular, we argue that most of the UNRL approaches either explicitly or implicit model and exploit context information of a node. Consequently, we propose a framework that casts a variety of approaches -- random walk based, matrix factorization and deep learning based -- into a unified context-based optimization function. We systematically group the methods based on their similarities and differences. We study the differences among these methods in detail which we later use to explain their performance differences (on downstream tasks). We conduct a large-scale empirical study considering 9 popular and recent UNRL techniques and 11 real-world datasets with varying structural properties and two common tasks -- node classification and link prediction. We find that there is no single method that is a clear winner and that the choice of a suitable method is dictated by certain properties of the embedding methods, task and structural properties of the underlying graph. In addition we also report the common pitfalls in evaluation of UNRL methods and come up with suggestions for experimental design and interpretation of results.