Variational co-embedding learning for attributed network clustering

Article Computer Science, Artificial Intelligence

Incremental Graph Computation: Anchored Vertex Tracking in Dynamic Social Networks

Taotao Cai et al.

Summary: User engagement has attracted attention in studying the decay and expansion of communities in online social networking platforms. Persuading critical users to stay active in the network and prevent cascading dropouts among friends is important. This article introduces the problem of tracking anchored users at each timestamp of evolving networks and proposes algorithms to solve it.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2023)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Graph Clustering via Variational Graph Emb e dding

Lin Guo et al.

Summary: This study proposes an innovative end-to-end graph clustering framework with a joint strategy to address complex problems in the non-Euclidean space, achieving unsupervised clustering of graph nodes. It introduces a variational graph auto-encoder algorithm based on GCN and a self-training mechanism to enhance the prediction accuracy of node categories effectively.

PATTERN RECOGNITION (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Robust cross-network node classification via constrained graph mutual information

Shuiqiao Yang et al.

Summary: In this paper, we propose a robust graph domain adaptive learning framework (RGDAL) for cross-network node classification. RGDAL utilizes an information-theoretic principle to filter noisy factors and learns noise-resistant and domain-invariant graph representations through graph convolutional networks and adversarial learning components. Experimental results demonstrate that RGDAL exhibits better robustness for cross-network node classification.

KNOWLEDGE-BASED SYSTEMS (2022)

添加到收藏夹

Article Computer Science, Information Systems