arXiv 2025 / Recommender Systems

Towards Practical Large-scale Dynamical Heterogeneous Graph Embedding: Cold-start Resilient Recommendation

A dynamic heterogeneous graph embedding study focused on recommendation settings where new users, items, and relations appear over time.

arXiv DOI Full publications

Research area

User reactivation, generative recommendation, dynamic retrieval, graph embedding, counterfactual watch-time prediction, and efficient CTR modeling form the main technical line.

Publication record

Authors
M Long, J Liu, Y Li, H Xiong, J Yan, K Wang, Y Cao, J Ding
Venue
arXiv preprint arXiv:2512.13120
Year
2025
Area
Recommender Systems