Research map / Graph learning / Knowledge and temporal graphs
Multi-Relational Graph Representation Learning with Bayesian Gaussian Process Network
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 GGPN rather than CompGCN | link prediction · FB15K-237 | MRR: 0.355 -> 0.361 | Helped |
| use GGPN rather than CompGCN | link prediction · WN18RR | MRR: 0.479 -> 0.481 | Helped |
| replace the adaptive RFF kernel with a linear kernel (ablation) | GGPN · FB15K-237 | MRR: 0.341 -> 0.361 | Hurt |
| replace the adaptive RFF kernel with an RBF kernel (ablation) | GGPN · FB15K-237 | MRR: 0.344 -> 0.361 | Hurt |
| replace the adaptive RFF kernel with a Laplacian kernel (ablation) | GGPN · FB15K-237 | MRR: 0.334 -> 0.361 | Hurt |
| replace the adaptive RFF kernel with a sigmoid kernel (ablation) | GGPN · FB15K-237 | MRR: 0.341 -> 0.361 | Hurt |
| vary the number of RFF features (ablation) | GGPN · FB15K-237 | MRR | Mixed |
| vary the number of RFF features (ablation) | GGPN · FB15K-237 | training time | Hurt |
| use GGPN instead of CompGCN | entity classification · MUTAG | accuracy: 76.47 -> 80.88 | Helped |
| use GGPN instead of CompGCN | entity classification · BGS | accuracy: 89.27 -> 93.10 | Helped |
| use GGPN instead of CompGCN | entity classification · AIFB | accuracy: 94.44 -> 95.83 | Mixed |
Closest papers by meaning
- Bayesian Semi-supervised Learning with Graph Gaussian Processes (NeurIPS 2018 · similarity 0.89)
- Dynamic Embedding on Textual Networks via a Gaussian Process (AAAI 2020 · similarity 0.88)
- Graph-Structured Gaussian Processes for Transferable Graph Learning (NeurIPS 2023 · similarity 0.88)
- Graph Neural Network-Inspired Kernels for Gaussian Processes in Semi-Supervised Learning (ICLR 2023 · similarity 0.88)
- Graph Convolutional Gaussian Processes (ICML 2019 · similarity 0.88)
- Learning Latent Graph Structures and their Uncertainty (ICML 2025 · 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.