← Back to all news
arXiv Machine Learning By Megha P, Harshit Kumar, Srajan Agarwal, Anirban Banerjee, Olaf Wolkenhauer, Saptarshi Bej

HyperFuse: Fast Self-Supervised Node Embeddings for Attributed Hypergraphs

Read the original on arXiv Machine Learning →

HyperFuse is a new, label‑free pipeline for fast self‑supervised node embeddings on attributed hypergraphs. It computes structural node coordinates via a spectral relaxation of hypergraph modularity, builds multi‑scale feature summaries with utility‑weighted hyperedges, and trains a lightweight encoder for only 100 epochs. In experiments on nine public hypergraphs, HyperFuse achieved 13–179× speed‑ups over baselines and matched or exceeded their accuracy on most downstream tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
4d ago

Towards One-for-All Foundation Model for Attributed Graph Clustering

The paper introduces OFAG, a foundation model designed for attributed graph clustering that can be trained once and applied to diverse graphs without graph‑specific tuning. It learns a reusable clustering strategy from synthetic graphs and uses a dimension‑agnostic encoder to handle varying feature spaces, producing clustering‑friendly node representations in a single forward pass. Across ten datasets, a frozen OFAG model outperforms baselines in both speed and clustering quality, and the authors provide code and pretrained checkpoints for easy adoption.

By Yunhui Liu, Xudong Jin, Kang Zhang, Danshuo An, Yu Xing, Te Song, Jia Liu, Tieke He
fine-tuning
More like this →