AI Paper Atlas

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

ICML 2026 · Graph learning › GNN architectures · approach: Graph rewiring and scalable message passing

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 changedWhereMeasuredEffect
add union graph (ablation)M-SEAL · YeastAUC: 69.80 -> 94.87Improved
add union graph (ablation)M-SEAL · DrugBankAUC: 70.34 -> 96.79Improved
add Gaussian noise matrix phi (ablation)M-SEAL · YeastAUC: 91.26 -> 94.87Improved
add demultiplexing (ablation)M-SEAL · YeastAUC: 90.34 -> 94.87Improved
add random mask (ablation)M-SEAL · YeastAUC: 89.62 -> 94.87Improved
add PReLU activation (ablation)M-SEAL · YeastAUC: 92.43 -> 94.87Improved
add regularization term L_O (ablation)M-SEAL · DrugBankAUC: 95.47 -> 96.79Improved
add clustering-based batching (ablation)M-SEAL · Yeastspeedup ratio: 12 -> 16Improved
add clustering-based batching (ablation)M-SEAL · DrugBankAUC: 96.80 -> 96.79No clear effect
use MIMO-LP multiplexing (n=50) instead of one-to-one SEALSEAL · YeastAUC: 95.46 -> 94.87Hurt
use MIMO-LP multiplexing (n=100) with NCNNCN · PPAHR@100: 61.19 -> 61.12No clear effect
use MIMO-LP instead of DM-SEAL data multiplexingDM-SEAL · YeastAUC: 86.68 -> 94.87Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy