AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Hypergraph Foundation Model

Yue Gao, Yifan Feng, Shiquan Liu, Xiangmin Han, ShaoYi DU, Zongze Wu, Han Hu

TPAMI 2025 · Graph learning › Knowledge and temporal graphs · approach: Knowledge graph embeddings · 12 citations (OpenAlex)

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 neighborhood-prediction fine-tuning to the LM features (ablation)Hyper-FM · Arxiv-Textaccuracy: 0.3231 -> 0.4189Improved
add neighborhood-prediction fine-tuning to the LM features (ablation)Hyper-FM · Movielens-Textaccuracy: 0.2852 -> 0.3464Improved
add neighborhood-prediction fine-tuning to the LM features (ablation)Hyper-FM · Pubmed-CC-Textaccuracy: 0.3967 -> 0.4009Improved
add neighborhood-prediction fine-tuning to the LM features (ablation)Hyper-FM · 11 TAHG datasetsaccuracyImproved
use LM features instead of BoW (ablation)Hyper-FM · 11 TAHG datasetsaccuracy: 0.3142 -> 0.3297 on GoodBook-Text favors BoWMixed
use LM features instead of BoW (ablation)Hyper-FM · Arxiv-Textaccuracy: 0.2786 -> 0.3231Improved
use multi-domain Hyper-FM pretraining instead of isolated sequential pretraining (IP)HyperGCL + HGNN · Cora-CC-Textaccuracy: 0.3268 -> 0.3706Improved
use multi-domain Hyper-FM pretraining instead of isolated sequential pretraining (IP)HyperGCL + HGNN · Arxiv-Textaccuracy: 0.3540 -> 0.4189Improved
isolated pretraining then fine-tuning instead of supervised HGNN onlyHGNN · Cora-CC-Textaccuracy: 0.3570 -> 0.3268Hurt
Hyper-FM pretraining before fine-tuning vs supervised HGNNHGNN · Pubmed-CC-Textaccuracy: 23.4%Improved
Hyper-FM pretraining before fine-tuning vs supervised HGNNHGNN · OGBN-Arxivaccuracy: 14.3%Improved
pretrain on Aminer-Text and transfer to PPI-Text (domain with different hyperedge degree distribution)HGNN · PPI-Textaccuracy: 18.07%Hurt

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