Research map / Graph learning / GNN architectures
Pareto-Based Heterogeneous Knowledge Distillation for MLPs on Graphs
Wenrui Zhao, Yijun Tian, Zhichao Xu, Yawei Wang, Chuxu Zhang
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 |
|---|---|---|---|
| distill HGNN teacher into MLP with HGKD instead of training MLP on raw features | MLP student · IMDB/DBLP | Macro-F1: IMDB 20%: 49.63 -> 57.12 (HAN teacher) | Improved |
| HGKD student vs HAN teacher on DBLP | HGKD student · DBLP | Macro-F1: 91.89 -> 91.21 (20% train) | Hurt |
| HGKD student vs HAN teacher on IMDB | HGKD student · IMDB | Macro-F1: 63.66 -> 65.06 (80% train) | Improved |
| multi-level HGKD vs GLNN single-level distillation (ablation) | MLP student · DBLP | Macro-F1: 87.32 -> 92.13 (20% train, best GLNN vs HGKD) | Improved |
| add limited neighbor features (HGKD-N) (ablation) | HGKD · IMDB | Macro-F1: 57.12 -> 58.52 (HAN, 20%) | Improved |
| add limited neighbor features (HGKD-N) (ablation) | HGKD · DBLP | Macro-F1: 94.03 -> 93.99 (HAN, 80%) | No clear effect |
| add Pareto-based multi-teacher learning (HGKD+) (ablation) | HGKD · IMDB | Macro-F1: 60.52 -> 60.50 (40%) vs 57.12 -> 57.76 (20% HAN) | Mixed |
| combine multi-teacher and neighbor info (HGKD-N+) (ablation) | HGKD+ · IMDB | Macro-F1: 65.06 -> 67.72 (80% vs HGKD-HAN) | Improved |
Closest papers by meaning
- Demystifying GNN-to-MLP Knowledge Transfer: Theoretical Grounding and Dual-Stream Distillation Method (AAAI 2026 · similarity 0.91)
- Distilling Holistic Knowledge With Graph Neural Networks (ICCV 2021 · similarity 0.90)
- Multi-Scale Distillation from Multiple Graph Neural Networks (AAAI 2022 · similarity 0.90)
- Boosting Graph Neural Networks via Adaptive Knowledge Distillation (AAAI 2023 · similarity 0.90)
- VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs (ICLR 2024 · similarity 0.89)
- Heterogeneous Graph Neural Network on Semantic Tree (AAAI 2025 · similarity 0.88)
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.
