Frequently Asked Questions
Frequently Asked Questions
Who is Jiandong Ding?
Jiandong Ding is a Principal Algorithm Expert at Huawei Technologies, focusing on RecSys, Causal Inference, and LLM Agents. His research philosophy is “From Biological Sequences to User Behaviors”, applying deep representation learning to decipher underlying patterns in data—from genomic sequences in his early career to billion-scale user behavior logs in commercial recommendation systems today.
What are Jiandong Ding’s main research areas?
Jiandong Ding’s research focuses on three core pillars:
- Generative & Trustworthy RecSys: Including LLM-driven Recommendation, Sequential Modeling, and User Representation.
- Trustworthy AI: Including Causal Inference, Unbiased Learning, and Fairness in Ranking.
- System Efficiency: Including Edge-Cloud Collaboration, Retrieval Architecture, and Model Compression.
Where did Jiandong Ding study?
Jiandong Ding studied at Fudan University. His early career focused on bioinformatics, specifically deciphering biological sequences, before transitioning to user behavior analysis in commercial recommendation systems.
What institutions does Jiandong Ding collaborate with?
Jiandong Ding collaborates with several institutions globally, including:
- Fudan University (Ongoing collaboration)
- Tongji University (Past collaboration)
- Nanjing University (Ongoing collaboration)
- Shanghai Jiao Tong University (Ongoing collaboration)
- Tsinghua University (Past collaboration)
- Southeast University (Past collaboration)
- Duke University (Past collaboration)
- Trinity College Dublin (Past collaboration)
- University of Houston (Past collaboration)
- Hong Kong Baptist University (Past collaboration)
What are some recent achievements of Jiandong Ding?
Recent achievements include papers accepted by top-tier venues such as ACM TOIS, TheWebConf (WWW) 2026, WSDM 2026, and AAAI 2026. Notable works include:
- HPGR framework for hierarchical generative recommendations
- Invariant feature learning for causal inference in recommendation systems
- RPE4Rec for high-efficiency dynamic retrieval
- Unified low-rank compression for CTR prediction
What is the focus of Jiandong Ding’s current research?
Currently, Jiandong Ding focuses on building Next-Generation Recommender Systems driven by Generative AI, with specific interests in Generative RecSys, Trustworthy AI, and System Efficiency, bridging the gap between theoretical algorithms and industrial-scale systems.