Geng Ji

RESEARCH SCIENTIST | MENLO PARK, UNITED STATES

Geng Ji is a research scientist at Facebook AI. His research interests are large-scale probabilistic inference, deep reinforcement learning, and their real-world applications ranging from recommendation systems to natural language processing. He is an expert of framing key challenges in complicated product environments into elegant machine learning models, and innovates scalable training algorithms never seen in the company before. Since he joined the company in 2019, Geng has led more than ten launches within Facebook and Instagram across multiple key products, including Ads, Feed, Friends, Groups and Marketplace, together with a track record of publications in top-tier ML conferences and journals such as ICML, UAI, WWW and Machine Learning. He got his PhD in computer science from UC Irvine with Professor Erik Sudderth, and finished his undergrad in engineering physics in Tsinghua University, China.

Geng's Work

Geng's Publications

January 06, 2024

RANKING AND RECOMMENDATIONS

REINFORCEMENT LEARNING

Learning to bid and rank together in recommendation systems

Geng Ji, Wentao Jiang, Jiang Li, Fahmid Morshed Fahid, Zhengxing Chen, Yinghua Li, Jun Xiao, Chongxi Bao, Zheqing (Bill) Zhu

January 06, 2024