Research map / Graph learning / GNN architectures
Subgraph Pattern Neural Networks for High-Order Graph Evolution Prediction
Changping Meng, S Chandra Mouli, Bruno Ribeiro, Jennifer Neville
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 |
|---|---|---|---|
| joint high-order subgraph pattern network (SPNN) instead of best joint baseline | subgraph evolution prediction · DBLP | AUC: 0.830 -> 0.846 | Improved |
| SPNN instead of best baseline | subgraph evolution prediction · Friendster Activity | AUC: 0.524 -> 0.690 | Improved |
| SPNN instead of best baseline | subgraph evolution prediction · Friendster Structure | AUC: 0.552 -> 0.607 | Improved |
| joint instead of independent link-prediction training for baselines | baselines · DBLP, Friendster | AUC | No clear effect |
| SPNN sparse pattern layer instead of fully connected MLP on same features (ablation) | SPNN · DBLP, Facebook, WordNet learning curves | AUC | Improved |
| add hidden pattern layer over logistic regression with same features (ablation) | SPNN · DBLP, Facebook, WordNet | AUC | Improved |
| SPNN features instead of Node2Vec/PCRW/PC/edge features (logistic regression) (ablation) | logistic regression · dynamic Facebook/WordNet | AUC | Improved |
| SPNN instead of Rescal/HolE | runtime · Friendster Activity | time: 28h32min -> 9min | Improved |
Closest papers by meaning
- Structure-Enhanced Adapter for Self-Supervised Heterogeneous Graph Learning (AAAI 2026 · similarity 0.89)
- An Efficient Subgraph-Inferring Framework for Large-Scale Heterogeneous Graphs (AAAI 2024 · similarity 0.89)
- Generative Graph Pattern Machine (NeurIPS 2025 · similarity 0.88)
- Beyond Message Passing: Neural Graph Pattern Machine (ICML 2025 · similarity 0.88)
- Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning (ICML 2024 · similarity 0.88)
- A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening (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.
