Research map / Graph learning / GNN architectures
Differentiable Meta Multigraph Search with Partial Message Propagation on Heterogeneous Information Networks
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 meta multigraph derivation instead of DiffMG's single-path derivation (ablation) | DiffMG search · DBLP | Macro-F1: 94.45$\pm$0.15 -> 94.75$\pm$0.11 | Helped |
| Use meta multigraph derivation instead of DiffMG's single-path derivation (ablation) | DiffMG search · ACM | Macro-F1: 92.65$\pm$0.15 -> 93.36$\pm$0.09 | Helped |
| Use meta multigraph derivation instead of DiffMG's single-path derivation (ablation) | DiffMG search · Amazon | AUC: 75.28$\pm$0.08 -> 75.32$\pm$0.04 | Helped |
| Use meta multigraph derivation instead of DiffMG's single-path derivation (ablation) | DiffMG search · Yelp | AUC: 68.77$\pm$0.13 -> 69.48$\pm$0.13 | Helped |
| Use meta multigraph derivation instead of DiffMG's single-path derivation (ablation) | DiffMG search · Douban | AUC: 83.78$\pm$0.09 -> 83.90$\pm$0.02 | Helped |
| Use meta multigraph derivation instead of DiffMG's single-path derivation (ablation) | DiffMG search · IMDB | Macro-F1: 61.04$\pm$0.56 -> 61.46$\pm$0.77 | Helped |
| Use meta multigraph derivation instead of DiffMG's single-path derivation (ablation) | DiffMG search · ACM | Micro-F1: 92.21$\pm$0.31 -> 93.27$\pm$0.09 | Helped |
| Use meta multigraph derivation instead of DiffMG's single-path derivation (ablation) | DiffMG search · DBLP | Micro-F1: 94.85$\pm$0.27 -> 95.38$\pm$0.13 | Helped |
| Use meta multigraph derivation instead of DiffMG's single-path derivation (ablation) | DiffMG search · IMDB | Micro-F1: 61.81$\pm$1.59 -> 63.44$\pm$1.01 | Helped |
| Use meta multigraph derivation instead of DiffMG's single-path derivation (ablation) | DiffMG search · Amazon | Search cost (GPU minutes): 0.7 -> 0.9 | Hurt |
| Use meta multigraph derivation instead of DiffMG's single-path derivation (ablation) | DiffMG search · Yelp | Search cost (GPU minutes): 1.1 -> 1.4 | Hurt |
| Use meta multigraph derivation instead of DiffMG's single-path derivation (ablation) | DiffMG search · Douban | Search cost (GPU minutes): 1.6 -> 2.1 | Hurt |
Closest papers by meaning
- Heterogeneous Graph Neural Network on Semantic Tree (AAAI 2025 · similarity 0.88)
- Hypergraph Neural Architecture Search (AAAI 2024 · similarity 0.86)
- Unified Graph Neural Networks Pre-training for Multi-domain Graphs (AAAI 2025 · similarity 0.85)
- Graph Metanetworks for Processing Diverse Neural Architectures (ICLR 2024 · similarity 0.85)
- Long-range Meta-path Search on Large-scale Heterogeneous Graphs (NeurIPS 2024 · similarity 0.85)
- An Efficient Subgraph-Inferring Framework for Large-Scale Heterogeneous Graphs (AAAI 2024 · 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.