Research map / Graph learning / Graph algorithms and clustering
Partition and Code: learning how to compress graphs
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 |
|---|---|---|---|
| Use PnC with neural partitioning instead of non-parametric SBM-Bayes | Graph compression · MUTAG | total bpe: 4.62 -> 2.45±0.02 | Helped |
| Use PnC with neural partitioning instead of non-parametric SBM-Bayes | Graph compression · PTC | total bpe: 5.12 -> 2.97±0.14 | Helped |
| Use PnC with Louvain partitioning instead of GraphRNN (pruned) | Graph compression · ZINC | total bpe: 2.02 -> 1.99 | Helped |
| Use PnC with neural partitioning instead of GraphRNN (pruned) | Graph compression · PROTEINS | total bpe: 3.76 -> 3.51±0.23 | Helped |
| Use PnC with SBM partitioning instead of non-parametric SBM-Bayes | Graph compression · IMDB-B | total bpe: 0.80 -> 0.54 | Helped |
| Use PnC with SBM partitioning instead of non-parametric SBM-Bayes | Graph compression · IMDB-M | total bpe: 0.60 -> 0.38 | Helped |
| Replace Louvain with neural partitioning within PnC (ablation) | PnC · MUTAG | total bpe: 2.51 -> 2.45±0.02 | Helped |
| Replace Louvain with neural partitioning within PnC (ablation) | PnC · PTC | total bpe: 3.14 -> 2.97±0.14 | Helped |
| Replace Louvain with neural partitioning within PnC (ablation) | PnC · ZINC | total bpe: 1.99 -> 2.07±0.03 | Hurt |
| Replace SBM with neural partitioning within PnC (ablation) | PnC · PROTEINS | total bpe: 3.60 -> 3.51±0.23 | Helped |
| Replace SBM with neural partitioning within PnC (ablation) | PnC · IMDB-B | total bpe: 0.54 -> 1.05±0.04 | Hurt |
| Replace SBM with neural partitioning within PnC (ablation) | PnC · IMDB-M | total bpe: 0.38 -> 0.72±0.05 | Hurt |
Closest papers by meaning
- Learning Graph Representation via Graph Entropy Maximization (ICML 2024 · similarity 0.87)
- Entropy Coding of Unordered Data Structures (ICLR 2024 · similarity 0.86)
- Practical Shuffle Coding (NeurIPS 2024 · similarity 0.86)
- StructComp: Substituting propagation with Structural Compression in Training Graph Contrastive Learning (ICLR 2024 · similarity 0.85)
- Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching (ICML 2024 · similarity 0.85)
- Graph Parsing Networks (ICLR 2024 · similarity 0.85)
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.