Graph Embedding

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, down 40% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 34

All topics

The Impact of Dimensionality on the Stability of Node Embeddings
Apr 9, 2026Tobias Schumacher, Simon Reichelt, Markus StrohmaierRepresentation Learning Algorithmic Stability
University of Mannheim · RWTH Aachen University · GESIS - Leibniz Institute for the Social Sciences, and +1
OntoTKGE: Ontology-Enhanced Temporal Knowledge Graph Extrapolation
Apr 7, 2026Dongying Lin, Yinan Liu, Shengwei tang +2KG Embedding Temporal Link Prediction
Northeastern University, Shenyang, China
Robustness of shallow graph embedding methods for community detection
May 1, 2024Zhi-Feng Wei, Pablo Moriano, Ramakrishnan KannanGraph Clustering Graph Embedding
Advanced Computing, Mathematics, and Data Division, Pacific Northwest National Laboratory, Richland, 99354, WA, USA. · Department of Mathematics, Indiana University, Bloomington, 47405, IN, USA. · Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, 37830, TN, USA.
Parametrized Power-Iteration Clustering for Directed Graphs
Oct 1, 2022Gwendal Debaussart-Joniec, Harry Sevi, Matthieu Jonckheere +1Graph Clustering Graph Embedding
Universit´e Paris-Saclay, ENS Paris-Saclay, Centre Borelli, CNRS, France · CNRS, LAAS, France

Apr 9, 2026, cs.LGJ/K move · Enter open · S save

The Impact of Dimensionality on the Stability of Node Embeddings

Tobias Schumacher, Simon Reichelt, Markus Strohmaier

University of Mannheim · RWTH Aachen University · GESIS - Leibniz Institute for the Social Sciences, and+1

Representation Learning Algorithmic Stability Graph Embedding

Open paper AskPDF arXiv

Previous work has shown that node embedding methods can produce different representations and downstream predictions across repeated training runs, even when trained on the same data with identical hyperparameters. However, the role of embedding dimensionality in this instability remains poorly understood. In this work, we systematically analyze how embedding dimensionality affects the stability of embeddings from five widely used node embedding methods: ASNE, DGI, GraphSAGE, node2vec, and VERSE. We evaluate stability from both representational and functional perspectives across a broad range of dimensions, datasets, and repeated training runs, and relate the resulting stability patterns to predictive performance. Our results show that dimensionality can substantially affect embedding stability, although the observed effects depend strongly on the embedding method and stability notion considered. While node2vec and ASNE generally became more stable at higher dimensions, GraphSAGE and VERSE often exhibited non-monotonic behavior or decreasing stability. We further find that dimensions associated with high stability do not necessarily coincide with those yielding the strongest downstream performance. Overall, our findings demonstrate that embedding dimensionality can have a substantial impact on the stability of node embeddings and downstream predictions.

Momentum

Related topics

Latest papers 34

The Impact of Dimensionality on the Stability of Node Embeddings

OntoTKGE: Ontology-Enhanced Temporal Knowledge Graph Extrapolation

Robustness of shallow graph embedding methods for community detection

Parametrized Power-Iteration Clustering for Directed Graphs