activity
20202022
most citedUnsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation

44 citations · 64 across the 5 of their papers we have counts for

collaborators

6 papers

cs.LG202211 cited

Graph Masked Autoencoders with Transformers

Sixiao Zhang, Hongxu Chen, Haoran Yang +3

Recently, transformers have shown promising performance in learning graph representations. However, there are still some challenges when applying transformers to real-world scenari…

cs.LG202244 cited

Unsupervised Graph Poisoning Attack via Contrastive Loss Back-propagation

Sixiao Zhang, Hongxu Chen, Xiangguo Sun +2

Graph contrastive learning is the state-of-the-art unsupervised graph representation learning framework and has shown comparable performance with supervised approaches. However, ev…

cs.SI20211 cited

Hyperbolic Hypergraphs for Sequential Recommendation

Yicong Li, Hongxu Chen, Xiangguo Sun +5

Hypergraphs have been becoming a popular choice to model complex, non-pairwise, and higher-order interactions for recommender system. However, compared with traditional graph-based…

cs.SI20211 cited

Temporal Meta-path Guided Explainable Recommendation

Hongxu Chen, Yicong Li, Xiangguo Sun +2

This paper utilizes well-designed item-item path modelling between consecutive items with attention mechanisms to sequentially model dynamic user-item evolutions on dynamic knowled…

cs.SI2020

Heterogeneous Hypergraph Embedding for Graph Classification

Xiangguo Sun, Hongzhi Yin, Bo Liu +4

Recently, graph neural networks have been widely used for network embedding because of their prominent performance in pairwise relationship learning. In the real world, a more natu…

cs.SI20207 cited

Multi-level Graph Convolutional Networks for Cross-platform Anchor Link Prediction

Hongxu Chen, Hongzhi Yin, Xiangguo Sun +3

Cross-platform account matching plays a significant role in social network analytics, and is beneficial for a wide range of applications. However, existing methods either heavily r…