Research map / Learning theory and algorithms / Clustering
Unsupervised Large Graph Embedding
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| ULGE (anchor graph, low-rank doubly stochastic similarity) vs SR | spectral dimensionality reduction · SensIT | running time: 1505.1 -> 91.5 | Helped |
| ULGE-K vs LE | spectral dimensionality reduction · MNIST | ACC: 68.4 -> 60.7 | Hurt |
| ULGE-K vs best competitor | spectral dimensionality reduction · USPS, Protein | ACC: 68.9 -> 69.3 (USPS) | Helped |
| use k-means anchors instead of random anchors (ablation) | ULGE · USPS, MNIST, Connect-4, SensIT | ACC: 54.9 -> 60.7 (MNIST) | Helped |
| use k-means anchors instead of random anchors (ablation) | ULGE · MNIST | running time: 8.8 -> 14.7 | Hurt |
| increase number of anchors (ablation) | ULGE · MNIST | ACC | Helped |
| increase number of anchors from 1000 to 2500 (ablation) | ULGE-K · MNIST | running time: 14.7 -> 34.3 | Hurt |
| increase down-sampling decimation factor (2 -> 10) (ablation) | ULGE-K anchor generation · MNIST | running time: 72.3 -> 14.7 | Helped |
| increase down-sampling decimation factor (ablation) | ULGE-K anchor generation · MNIST | ACC | Hurt |
Closest papers by meaning
- Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding (NeurIPS 2023 · similarity 0.85)
- Simple Unsupervised Graph Representation Learning (AAAI 2022 · similarity 0.85)
- How Low Can You Go? Searching for the Intrinsic Dimensionality of Complex Networks using Metric Node Embeddings (ICLR 2025 · similarity 0.85)
- Structure-Aware Spectral Sparsification via Uniform Edge Sampling (NeurIPS 2025 · similarity 0.84)
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · similarity 0.84)
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · similarity 0.83)
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.