Research map / Graph learning / Graph self-supervised learning
HARP: Hierarchical Representation Learning for Networks
Haochen Chen, Bryan Perozzi, Yifan Hu, Steven Skiena
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 |
|---|---|---|---|
| Apply HARP hierarchical coarsening and refinement to DeepWalk | DeepWalk · DBLP classification | Macro F1: 57.29 -> 61.76 | Improved |
| Apply HARP hierarchical coarsening and refinement to LINE | LINE · DBLP classification | Macro F1: 57.76 -> 59.51 | Improved |
| Apply HARP hierarchical coarsening and refinement to Node2vec | Node2vec · DBLP classification | Macro F1: 62.64 -> 62.80 | Improved |
| Apply HARP hierarchical coarsening and refinement to DeepWalk | DeepWalk · BlogCatalog classification | Macro F1: 24.88 -> 25.90 | Improved |
| Apply HARP hierarchical coarsening and refinement to LINE | LINE · BlogCatalog classification | Macro F1: 22.43 -> 23.47 | Improved |
| Apply HARP hierarchical coarsening and refinement to Node2vec | Node2vec · BlogCatalog classification | Macro F1: 23.55 -> 24.66 | Improved |
| Apply HARP hierarchical coarsening and refinement to DeepWalk | DeepWalk · CiteSeer classification | Macro F1: 42.72 -> 44.78 | Improved |
| Apply HARP hierarchical coarsening and refinement to LINE | LINE · CiteSeer classification | Macro F1: 37.11 -> 42.95 | Improved |
| Apply HARP hierarchical coarsening and refinement to Node2vec | Node2vec · CiteSeer classification | Macro F1: 44.84 -> 46.08 | Improved |
Closest papers by meaning
- Fisher Information Embedding for Node and Graph Learning (ICML 2023 · similarity 0.88)
- Learning Representations for Hierarchies with Minimal Support (NeurIPS 2024 · similarity 0.88)
- GEM: A Dual-Scale Architecture for Graph-Level Hierarchical Representation Learning (NeurIPS 2026 · similarity 0.88)
- Asymptotics of Network Embeddings Learned via Subsampling (JMLR 2023 · similarity 0.87)
- GraphZoom: A Multi-level Spectral Approach for Accurate and Scalable Graph Embedding (ICLR 2020 · similarity 0.87)
- Weighted Embeddings for Low-Dimensional Graph Representation (AAAI 2025 · 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.
