Research map / Graph learning / Graph algorithms and clustering
Joint Embedding of Graphs
Shangsi Wang, Jesús Arroyo, Joshua T Vogelstein, Carey E. Priebe
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| initialize with SVD of average residual instead of one random start (ablation) | joint embedding · MREG simulation | Objective (lower better): 383.29 -> 375.22 | Improved |
| initialize with SVD instead of best of 10 random starts (ablation) | joint embedding · MREG simulation | Objective (lower better): 379.63 -> 375.22 | Improved |
| initialize with SVD instead of best of 10 random starts (ablation) | joint embedding · MREG simulation | Running time (sec.): 96.5 -> 8.3 | Improved |
| initialize with true components instead of SVD (ablation) | joint embedding · MREG simulation | Objective (lower better): 375.22 -> 374.69 | No clear effect |
| use joint embedding of both graphs instead of ASE on French graph alone | spectral clustering · Wikipedia French graph | Adjusted Rand index: 0.114 -> 0.154 | Improved |
| use joint embedding instead of ASE on English graph | spectral clustering · Wikipedia English graph | Adjusted Rand index: 0.152 -> 0.154 | No clear effect |
| use joint latent positions instead of ASE on mean graph | spectral clustering · Wikipedia joint graphs | Adjusted Rand index: 0.155 -> 0.156 | No clear effect |
| use joint embedding instead of PCA with few dimensions | 1-NN subject classification · HNU1 (one scan per subject) | classification accuracy | Improved |
| use joint embedding instead of ASE, LE, GS, GSS, PCA features | 1-NN graph classification · MREG classification simulation | classification accuracy | Improved |
Closest papers by meaning
- GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding (ICLR 2020 · similarity 0.90)
- Co-Embedding of Nodes and Edges With Graph Neural Networks (TPAMI 2020 · similarity 0.89)
- Multi-View Multi-Graph Embedding for Brain Network Clustering Analysis (AAAI 2018 · similarity 0.89)
- Fisher Information Embedding for Node and Graph Learning (ICML 2023 · similarity 0.88)
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.87)
- How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
