collaborators

6 papers

cs.SI2026

PDSL: Propagation Dynamics Aware Framework for Source Localization

Yansong Wang, Qisen Chai, Longlong Lin +1

Source localization is a representative inverse inference task in information propagation, aiming to identify the source node or node set that triggers the propagation results base…

cs.LG2026

Robust Smart Contract Vulnerability Detection via Contrastive Learning-Enhanced Granular-ball Training

Zeli Wang, Qingxuan Yang, Shuyin Xia +3

Deep neural networks (DNNs) have emerged as a prominent approach for detecting smart contract vulnerabilities, driven by the growing contract datasets and advanced deep learning te…

cs.LG2026

From Representation to Clusters: A Contrastive Learning Approach for Attributed Hypergraph Clustering

Li Ni, Shuaikang Zeng, Lin Mu +1

Contrastive learning has demonstrated strong performance in attributed hypergraph clustering. Typically, existing methods based on contrastive learning first learn node embeddings…

cs.SI2025

NCSAC: Effective Neural Community Search via Attribute-augmented Conductance

Longlong Lin, Quanao Li, Miao Qiao +5

Identifying locally dense communities closely connected to the user-initiated query node is crucial for a wide range of applications. Existing approaches either solely depend on ru…

cs.SI2025

Effective and Efficient Conductance-based Community Search at Billion Scale

Longlong Lin, Yue He, Wei Chen +3

Community search is a widely studied semi-supervised graph clustering problem, retrieving a high-quality connected subgraph containing the user-specified query vertex. However, exi…

cs.LG2025

CoATA: Effective Co-Augmentation of Topology and Attribute for Graph Neural Networks

Tao Liu, Longlong Lin, Yunfeng Yu +4

Graph Neural Networks (GNNs) have garnered substantial attention due to their remarkable capability in learning graph representations. However, real-world graphs often exhibit subs…