Research map / Graph learning / GNN architectures
MIMO-LP: A Multi-Input Multi-Output Framework for Subgraph-based Link Prediction
Yixin Song, Guangchi Liu, Xiangyu Xu, Shaofeng Li, Zhen Ling, Yiwei Wang, Yujun Cai
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 union graph (ablation) | M-SEAL · Yeast | AUC: 69.80 -> 94.87 | Improved |
| add union graph (ablation) | M-SEAL · DrugBank | AUC: 70.34 -> 96.79 | Improved |
| add Gaussian noise matrix phi (ablation) | M-SEAL · Yeast | AUC: 91.26 -> 94.87 | Improved |
| add demultiplexing (ablation) | M-SEAL · Yeast | AUC: 90.34 -> 94.87 | Improved |
| add random mask (ablation) | M-SEAL · Yeast | AUC: 89.62 -> 94.87 | Improved |
| add PReLU activation (ablation) | M-SEAL · Yeast | AUC: 92.43 -> 94.87 | Improved |
| add regularization term L_O (ablation) | M-SEAL · DrugBank | AUC: 95.47 -> 96.79 | Improved |
| add clustering-based batching (ablation) | M-SEAL · Yeast | speedup ratio: 12 -> 16 | Improved |
| add clustering-based batching (ablation) | M-SEAL · DrugBank | AUC: 96.80 -> 96.79 | No clear effect |
| use MIMO-LP multiplexing (n=50) instead of one-to-one SEAL | SEAL · Yeast | AUC: 95.46 -> 94.87 | Hurt |
| use MIMO-LP multiplexing (n=100) with NCN | NCN · PPA | HR@100: 61.19 -> 61.12 | No clear effect |
| use MIMO-LP instead of DM-SEAL data multiplexing | DM-SEAL · Yeast | AUC: 86.68 -> 94.87 | Improved |
Closest papers by meaning
- Subgraph Encoding with Bicentric Sphere Node Labeling and Pooling for Link Prediction (AAAI 2026 · similarity 0.88)
- GNNs Meet Sequence Models Along the Shortest-Path: an Expressive Method for Link Prediction (NeurIPS 2026 · similarity 0.87)
- Future Link Prediction Without Memory or Aggregation (NeurIPS 2025 · similarity 0.86)
- Revisiting Link Prediction: a data perspective (ICLR 2024 · similarity 0.86)
- Pure Message Passing Can Estimate Common Neighbor for Link Prediction (NeurIPS 2024 · similarity 0.85)
- Structural Information Enhanced Graph Representation for Link Prediction (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.
