Zhen Fang and Jie Lu awarded NeurIPS 'Outstanding Paper'
Dr Zhen Fang and Distinguished Professor Jie Lu's paper was one of only 13 selected for the NeurIPS 'Outstanding Paper' Award from a total of 10,411 submissions.
AAII Researchers Awarded 'Outstanding Paper' at NeurIPS 2022
Discover: Australian Laureate Fellow Project - Autonomous Learning
Postdoc Fellow Dr Zhen Fang (first author) and his supervisor, Australian Laureate Fellow, Distinguished Professor Jie Lu (corresponding author) have received the Outstanding Paper Award for their co-authored paper “Is Out-of-Distribution Detection Learnable?” at the 36th Conference on Neural Information Processing Systems (NeurIPS 2022).
NeurIPS conference is one of the most prestigious and competitive international conferences in artificial intelligence and machine learning. NeurIPS 2022 received 10,411 submissions with approximately 25% acceptance rate, and only 13 papers were selected for the Outstanding Paper Awards.
As highly commended by the NeurIPS 2022 Awards Committee, the awarded paper provides a highly significant theoretical study of out-of-distribution (OOD) detection, focusing on the conditions under which such models are learnable. It provides a theoretical grounding for existing OOD detection approaches. It also raises new theoretical questions about the learnability of near-OOD detection. As such, this research, which is supported by Distinguished Professor Jie Lu's Arc Laureate Fellow project, has the potential for broad theoretical and practical impact in this important field.
The first author, Dr Zhen Fang, works on transfer learning, out-of-distribution learning, and machine learning theory. "It is a great encouragement to us! I am honored to receive such a prestigious award from the artificial intelligence and machine learning international research community," said Dr Fang.
Read the full paper: "Is Out-of-Distribution Detection Learnable?"