JD AI Research (2020)

Position

Research Intern (05/2020 - 08/2020), JD AI Research, Mountain View, USA.

Supervised by Dr. Jing Huang & Dr. Guangtao Wang (JD AI Research), in collaboration with Stanford University.

Research

During my internship at JD AI Research, I focused on commonsense knowledge graph completion and inductive learning for knowledge representation.

The research addressed a critical challenge in commonsense knowledge graphs (CKGs): how to perform knowledge graph completion for entities unseen during training (inductive learning). Traditional methods required retraining when new entities were added, which is impractical for large-scale CKGs.

We developed InductivE, a novel learning framework for inductive knowledge graph completion. The framework consists of three key components: a free-text encoder for processing entity descriptions, a graph encoder for capturing structural information, and a KG completion decoder for predicting missing relations.

Technical Work

• Designed and implemented the InductivE framework for inductive commonsense knowledge graph completion
• Developed free-text encoder using pre-trained language models to encode entity descriptions
• Built graph neural network encoder to capture structural information from the knowledge graph
• Implemented knowledge graph completion decoder for relation prediction
• Conducted extensive experiments on ATOMIC and ConceptNet benchmarks

Key Achievements

• Achieved over 48% improvement in inductive scenarios compared to existing methods
• State-of-the-art results on ATOMIC and ConceptNet benchmarks
• Published research paper at IJCNN 2021 (International Joint Conference on Neural Networks)
• Framework enables handling of unseen entities without model retraining

Publication