Research map / Graph learning / Graph algorithms and clustering
Online Graph Dictionary Learning
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 |
|---|---|---|---|
| Add negative quadratic sparsity regularization (ablation) | GDL · IMDB-B | Rand Index: 51.32(0.30) -> 51.64(0.59) | Helped |
| Add negative quadratic sparsity regularization (ablation) | GDL · IMDB-M | Rand Index: 55.08(0.28) -> 55.41(0.20) | Helped |
| Add negative quadratic sparsity regularization (ablation) | GDL · MUTAG | Rand Index: 70.02(0.29) -> 70.89(0.11) | Helped |
| Add negative quadratic sparsity regularization (ablation) | GDL · PTC-MR | Rand Index: 51.53(0.36) -> 51.90(0.54) | Helped |
| Add negative quadratic sparsity regularization (ablation) | GDL · BZR | Rand Index: 62.59(1.68) -> 66.42(1.96) | Helped |
| Add negative quadratic sparsity regularization (ablation) | GDL · COX2 | Rand Index: 58.39(0.52) -> 59.48(0.68) | Helped |
| Add negative quadratic sparsity regularization (ablation) | GDL · ENZYMES | Rand Index: 66.97(0.93) -> 66.79(1.12) | Hurt |
| Add negative quadratic sparsity regularization (ablation) | GDL · PROTEIN | Rand Index: 60.22(0.30) -> 60.49(0.71) | Helped |
| Use GDL_lambda rather than GWF-r | Graph clustering · ENZYMES | Rand Index: 72.13(0.19) vs 66.79(1.12) | Hurt |
| Use GDL_lambda rather than GWF-r | Graph clustering · MUTAG | Rand Index: 68.83(1.47) vs 70.89(0.11) | Helped |
| Use learned node weights instead of uniform weights (ablation) | GDL on IMDB-M · IMDB-M | graph structure fidelity | Helped |
| Use the Mahalanobis upper bound in place of direct GW distances | GDL embedding comparisons on simulated D1 · D1 | distance correlation: 0.96 | Helped |
Closest papers by meaning
- Semi-relaxed Gromov-Wasserstein divergence and applications on graphs (ICLR 2022 · similarity 0.92)
- Generative Graph Dictionary Learning (ICML 2023 · similarity 0.91)
- Scalable Gromov-Wasserstein Learning for Graph Partitioning and Matching (NeurIPS 2019 · similarity 0.88)
- THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings (AAAI 2025 · similarity 0.86)
- Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models (NeurIPS 2025 · similarity 0.84)
- Learning Graph Representation via Graph Entropy Maximization (ICML 2024 · similarity 0.84)
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.