works on

From the 1 of 13 linked papers with an AI index.

activity
20242026
collaborators

13 papers

cs.SI2026

Comprehensive, Efficient Large-Scale Community Detection via Structural Entropy Game

Pu Li, Yantuan Xian, Hao Peng +4

The paper introduces CoDeSEG, a heuristic algorithm that detects non‑overlapping, overlapping, and dynamic communities in very large graphs by minimizing a two‑dimensional structur…

cs.LG2026

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

Jingyun Zhang, Hao Peng, Jianxin Li +2

Unsupervised graph clustering is a fundamental technique for uncovering underlying semantic patterns in large-scale networks. Although Graph Contrastive Learning has demonstrated p…

cs.CL2026

SeSE: Black-Box Uncertainty Quantification for Large Language Models Based on Structural Information Theory

Xingtao Zhao, Hao Peng, Dingli Su +4

Reliable uncertainty quantification (UQ) is essential for deploying large language models (LLMs) in safety-critical scenarios, as it enables them to abstain from responding when un…

cs.SI2026

Effective and Unsupervised Social Event Detection and Evolution via RAG and Structural Entropy

Qitong Liu, Hao Peng, Zuchen Li +5

With the growing scale of social media, social event detection and evolution modeling have attracted increasing attention. Graph neural networks (GNNs) and transformer-based pre-tr…

cs.LG2025

Hyperbolic Continuous Structural Entropy for Hierarchical Clustering

Guangjie Zeng, Hao Peng, Angsheng Li +5

Hierarchical clustering is a fundamental machine-learning technique for grouping data points into dendrograms. However, existing hierarchical clustering methods encounter two prima…

cs.LG2025

RoBCtrl: Attacking GNN-Based Social Bot Detectors via Reinforced Manipulation of Bots Control Interaction

Yingguang Yang, Xianghua Zeng, Qi Wu +5

Social networks have become a crucial source of real-time information for individuals. The influence of social bots within these platforms has garnered considerable attention from…