Hugging Face Trending Papers June 29, 2026

Curvature-Guided Sheaf Diffusion for Unsupervised Community Detection on Heterophilic Graphs

Read the original on Hugging Face Trending Papers →

Detecting communities in heterophilic graphs -- where connected nodes often belong to different classes -- is hard for unsupervised methods: classical modularity and spectral methods are feature agnostic, while deep graph-clustering methods rely on contrastive or generative machinery that is opaque. We propose Curvature-Guided Sheaf Diffusion (CGSD), a fully unsupervised community-detection algorithm that uses the discrete Forman--Ricci curvature of each edge as its single topological signal, propagated through every stage of an end-to-end pipeline.

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 Hugging Face Trending Papers.

arXiv AI

Jun 30

Curvature-Guided Sheaf Diffusion for Unsupervised Community Detection on Heterophilic Graphs

arXiv:2606. 30249v1 Announce Type: cross Abstract: Detecting communities in heterophilic graphs -- where connected nodes often belong to different classes -- is hard for unsupervised methods: classical modularity and spectral methods are feature agnostic, while deep graph-clustering methods rely on contrastive or generative machinery that is opaque.

By Feifan Wang

rag diffusion benchmarks

arXiv Machine Learning

Jul 27

Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature

arXiv:2607. 22381v1 Announce Type: new Abstract: Curvature notions on graphs, particularly Ollivier-Ricci and Forman, have emerged as powerful tools for addressing fundamental issues in Graph Neural Networks (GNNs) such as oversmoothing and oversquashing, but rely almost exclusively on local edge-level comparisons and therefore fail to certify how information actually propagates over long distances.

By Rachid Caich, Yassine Abbahaddou

efficiency benchmarks

arXiv AI

Jul 8

Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy

arXiv:2607. 05469v1 Announce Type: cross Abstract: Unsupervised graph clustering is a fundamental technique for uncovering underlying semantic patterns in large-scale networks.

By Jingyun Zhang, Hao Peng, Jianxin Li, Angsheng Li, Philip S. Yu

benchmarks

arXiv Machine Learning

Jun 16

Ricci-Filtration: Boosting Retrieval-Augmented Generation Reranker to Query-Answer Tasks by Discrete Ricci Flow

arXiv:2606. 15482v1 Announce Type: cross Abstract: Ricci flow is a curvature-guided diffusion process that deforms space by shrinking regions of high positive curvature and expanding those with negative curvature.

By Tian Qin, Wei-Min Huang

rag diffusion benchmarks

arXiv Machine Learning

Jun 9

Alcmean's: Unsupervised community detection using local Laplacian, automatic detection of the number of centers

arXiv:2606. 09100v1 Announce Type: cross Abstract: Community detection is a fundamental problem in the analysis of complex networks.

By Shahin Momenzadeh, Rojiar Pir Mohammadiani

rag benchmarks

arXiv Machine Learning

Jul 30

ReDiSC: A Reparameterized Masked Diffusion Model for Scalable Node Classification with Structured Predictions

arXiv:2507. 14484v2 Announce Type: replace Abstract: In recent years, graph neural networks (GNN) have achieved unprecedented successes in node classification tasks.

By Yule Li, Yifeng Lu, Zhen Wang, Zhewei Wei, Yaliang Li, Bolin Ding

diffusion computer-vision benchmarks

One email a morning, machine-written

Related stories

Curvature-Guided Sheaf Diffusion for Unsupervised Community Detection on Heterophilic Graphs

Local-Global Geometric Insights for Graph Neural Networks via Entropic Curvature

Breaking Structural Isolation: Scalable Graph Clustering via Community-Aware Sampling and Structural Entropy

Ricci-Filtration: Boosting Retrieval-Augmented Generation Reranker to Query-Answer Tasks by Discrete Ricci Flow

Alcmean's: Unsupervised community detection using local Laplacian, automatic detection of the number of centers

ReDiSC: A Reparameterized Masked Diffusion Model for Scalable Node Classification with Structured Predictions