no code implementations • 13 Dec 2023 • Yu Duan, Matthew Eaton, Michael Bluck
In this paper, we introduce an efficient sparse Gaussian process (E-SGP) for the surrogate modelling of fluid mechanics.
1 code implementation • 7 Feb 2023 • Yu Duan, Zhongfan Jia, Qian Li, Yi Zhong, Kaisheng Ma
Comparing different plasticity rules under the same framework shows that Hebbian plasticity is well-suited for several memory and associative learning tasks; however, it is outperformed by gradient-based plasticity on few-shot regression tasks which require the model to infer the underlying mapping.
no code implementations • 7 Jun 2022 • Jiannan Guo, Yangyang Kang, Yu Duan, Xiaozhong Liu, Siliang Tang, Wenqiao Zhang, Kun Kuang, Changlong Sun, Fei Wu
Motivated by the industry practice of labeling data, we propose an innovative Inconsistency-based virtual aDvErsarial Active Learning (IDEAL) algorithm to further investigate SSL-AL's potential superiority and achieve mutual enhancement of AL and SSL, i. e., SSL propagates label information to unlabeled samples and provides smoothed embeddings for AL, while AL excludes samples with inconsistent predictions and considerable uncertainty for SSL.
no code implementations • 15 Sep 2020 • Yu Duan, Matthew Eaton, Michael Bluck
This paper proposes a novel fixed inducing points online Bayesian calibration (FIPO-BC) algorithm to efficiently learn the model parameters using a benchmark database.
no code implementations • ACL 2020 • Zhuoren Jiang, Zhe Gao, Yu Duan, Yangyang Kang, Changlong Sun, Qiong Zhang, Xiaozhong Liu
We propose a Semi-supervIsed GeNerative Active Learning (SIGNAL) model to address the imbalance, efficiency, and text camouflage problems of Chinese text spam detection task.
1 code implementation • ACL 2020 • Yu Duan, Canwen Xu, Jiaxin Pei, Jialong Han, Chenliang Li
Conditional Text Generation has drawn much attention as a topic of Natural Language Generation (NLG) which provides the possibility for humans to control the properties of generated contents.
no code implementations • 22 Dec 2018 • Chenliang Li, Yu Duan, Haoran Wang, Zhiqian Zhang, Aixin Sun, Zongyang Ma
Recent studies show that the Dirichlet Multinomial Mixture (DMM) model is effective for topic inference over short texts by assuming that each piece of short text is generated by a single topic.
1 code implementation • ACL 2018 • Chenliang Li, Wei Zhou, Feng Ji, Yu Duan, Haiqing Chen
In the era of big data, focused analysis for diverse topics with a short response time becomes an urgent demand.