Research map / Graph learning / Graph self-supervised learning
Heterogeneous Graph Masked Autoencoders
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 HGMAE instead of the strongest clustering baseline HeCo | heterogeneous graph node clustering · DBLP, Freebase, ACM, and AMiner | NMI and ARI | Helped |
| Add metapath-based edge reconstruction (MER) (ablation) | HGMAE · Node classification on DBLP, Freebase, ACM, and AMiner | Mi-F1 | Helped |
| Add target attribute restoration (TAR) (ablation) | HGMAE · Node classification on DBLP, Freebase, ACM, and AMiner | Mi-F1 | Helped |
| Add positional feature prediction (PFP) (ablation) | HGMAE · Node classification on DBLP, Freebase, ACM, and AMiner | Mi-F1 | Helped |
| Use a dynamic attribute mask rate rather than a fixed rate | HGMAE · DBLP and Freebase mask-rate evaluation | node classification performance | Helped |
| Use leaving-unchanged and replacing techniques during attribute masking | HGMAE · DBLP and Freebase | node embedding performance | Helped |
Closest papers by meaning
- Self-supervised Masked Graph Autoencoder via Structure-aware Curriculum (ICML 2025 · similarity 0.93)
- Teacher-guided Edge Discriminator for Personalized Graph Masked Autoencoder (AAAI 2025 · similarity 0.91)
- Rethinking Graph Masked Autoencoders through Alignment and Uniformity (AAAI 2024 · similarity 0.90)
- HGOT: Self-supervised Heterogeneous Graph Neural Network with Optimal Transport (ICML 2025 · similarity 0.86)
- What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding (ICML 2024 · similarity 0.86)
- The quest for the GRAph Level autoEncoder (GRALE) (NeurIPS 2025 · similarity 0.86)
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.