Research map / Graph learning / Graph self-supervised learning
Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
Dasol Hwang, Jinyoung Park, Sunyoung Kwon, KyungMin Kim, Jung-Woo Ha, Hyunwoo J Kim
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 |
|---|---|---|---|
| add meta-path prediction auxiliary tasks with standard loss (ablation) | GNNs · Last-FM | AUC: +0.0106 avg gain | Improved |
| learn auxiliary task weights via meta-learning (SELAR) instead of standard auxiliary loss (ablation) | GNNs · Last-FM | AUC: +0.0106 -> +0.0190 avg gain | Improved |
| add Hint Network to SELAR (ablation) | SELAR · Last-FM | AUC: +0.0190 -> +0.0200 avg gain | Improved |
| add Hint Network to SELAR (ablation) | SELAR with GCN · Last-FM | AUC: 0.8296 -> 0.8121 | Hurt |
| add meta-path auxiliary tasks and SELAR (ablation) | GNNs · Book-Crossing | AUC: +0.0263 avg gain (SELAR) | Improved |
| add SELAR with meta-paths | GAT · IMDB | F1: 0.5653 -> 0.6099 | Improved |
| add SELAR and Hint (ablation) | GNNs · ACM | F1: +0.0079 / +0.0090 avg gain | Improved |
| learn sample weighting only without meta-path tasks (ablation) | GNNs · Last-FM | AUC: -0.0017 avg gain | No clear effect |
| learn sample weighting only without meta-path tasks (ablation) | GNNs · IMDB | F1: -0.0027 avg gain | No clear effect |
| use 3-fold meta cross-validation instead of 1-fold meta-data (ablation) | SELAR · Last-FM | AUC: 0.7885 -> 0.8296 (GCN) | Improved |
Closest papers by meaning
- Heterogeneous Graph Neural Network on Semantic Tree (AAAI 2025 · similarity 0.89)
- HGOT: Self-supervised Heterogeneous Graph Neural Network with Optimal Transport (ICML 2025 · similarity 0.88)
- Contrastive Auxiliary Learning with Structure Transformation for Heterogeneous Graphs (AAAI 2025 · similarity 0.88)
- HeterSEED: Semantics–Structure Decoupling for Heterogeneous Graph Learning under Heterophily (NeurIPS 2026 · similarity 0.88)
- Bootstrapping Heterogeneous Graph Representation Learning via Large Language Models: A Generalized Approach (AAAI 2025 · similarity 0.87)
- On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks (NeurIPS 2024 · similarity 0.87)
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.
