Xiran Song

Xiran Song

Auto-generated profile, based on publicly available information

Xiran Song

Washington University in St. Louis, SAINT LOUIS, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 April 2023
Verified
Conference Paper
Open access
XSXiran Song
Xiran Song
JLJianxun Lian
Jianxun Lian
HHHong Huang
Hong Huang
ZLZihan Luo
Zihan Luo
WZWei Zhou
Wei Zhou
HJHai Jin
Hai Jin
Graph neural networks (GNNs) have seen widespread usage across multiple real-world applications, yet in transductive learning, they still face challenges in accuracy, efficiency, and scalability, due to the extensive number of trainable parameters in the embedding table and the paradigm of stacking neighborhood aggregations. This paper presents a novel model called xGCN for large-scale network embedding, which is a practical solution for link predictions. xGCN addresses these issues by encoding graph-structure data in an extreme convolutional manner, and has the potential to push the performance of network embedding-based link predictions to a new record. Specifically, instead of assigning each node with a directly learnable embedding vector, xGCN regards node embeddings as static features. It uses a propagation operation to smooth node embeddings and relies on a Refinement neural Network (RefNet) to transform the coarse embeddings derived from the unsupervised propagation into new ones that optimize a training objective. The output of RefNet, which are well-refined embeddings, will replace the original node embeddings. This process is repeated iteratively until the model converges to a satisfying status. Experiments on three social network datasets with link prediction tasks show that xGCN not only achieves the best accuracy compared with a series of competitive baselines but also is highly efficient and scalable.

19 June 2023 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
WZWei Zhou
Wei Zhou
HHHong Huang
Hong Huang
RSRuize Shi
Ruize Shi
XSXiran Song
Xiran Song
XLXue Lin
Xue Lin
HJHai Jin
Hai Jin
Real-world networks are often heterogeneous and constantly changing over time. Evolution reveals the trend of network development, which is vital for predicting its future state, and network embedding can effectively learn the information from it. Nevertheless, previous works only consider the impact of meta-path instances or node neighbors on the network dynamics but ignore the relationship between them, and hence the hidden semantic information is missed, which will result in performance deterioration. Therefore, we propose a novel temporal heterogeneous information network embedding method (SemE), which abstracts the instance of the meta-path as semantic units and then considers the interaction between them to discover deeper semantic information. Specifically, we first construct semantic networks by the Ethernet topology and the interaction between semantic units. The semantic units are sampled based on a pre-designed meta-path-guided random walk. To further capture the semantic evolution of the semantic network, we learn the embedding of nodes by the attention-Hawkes process. Finally, we generate the final embedding by aggregating the structure, semantic and temporal information with the attention mechanism. Experiments on three real-world temporal heterogeneous information networks show that our model performs better than competitive counterparts.

20 July 2025
Verified
Conference Paper
Open access
ZLZihan Luo
Zihan Luo
HHHong Huang
Hong Huang
JLJianxun Lian
Jianxun Lian
XSXiran Song
Xiran Song
HJHai Jin
Hai Jin