README.md

Publications in WSDM 2021

Graph-based Semi-Supervised Learning

• Node Similarity Preserving Graph Convolutional Networks
• GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks

Heterogeneous Structures

• Heterogeneous Hypergraph Embedding for Graph Classification
• HeteGCN: Heterogeneous Graph Convolutional Networks for Text Classification
• BiTe-GCN: A New GCN Architecture via Bidirectional Convolution of Topology and Features on Text-Rich Networks
• Heterogeneous Graph Augmented Multi-Scenario Sharing Recommendation with Tree-Guided Expert Networks

Temporal Structures

• Modeling Inter-station Relationships with Attentive Temporal Graph Convolutional Network for Air Quality Prediction
• Time-Series Event Prediction with Evolutionary State Graph

Adversarial Learning / Robustness

• Adversarial Immunization for Certifiable Robustness on Graphs
• Learning to Drop: Robust Graph Neural Network via Topological Denoising
• Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information

Recommendation

• An Efficient and Effective Framework for Session-based Social Recommendation
• Decomposed Collaborative Filtering: Modeling Explicit and Implicit Factors For Recommender Systems

Cold-Start Recommendation

• Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation
• Alleviating Cold-Start Problems in Recommendation through Pseudo-Labelling over Knowledge Graph

Social Networks

• DeepIS: Susceptibility Estimation on Social Networks
• Discovering Undisclosed Paid Partnership on Social Media via Aspect-Attentive Sponsored Post Learning