no code implementations • 10 May 2024 • Tong Xiao, Jiayu Liu, Zhenya Huang, Jinze Wu, Jing Sha, Shijin Wang, Enhong Chen
Knowledge System controls an implicit reasoning process, which is responsible for providing diagram information and geometry knowledge according to a step-wise reasoning goal generated by Inference System.
1 code implementation • 10 Mar 2024 • Liyang He, Zhenya Huang, Jiayu Liu, Enhong Chen, Fei Wang, Jing Sha, Shijin Wang
In this paper, we propose an innovative Bit-mask Robust Contrastive knowledge Distillation (BRCD) method, specifically devised for the distillation of semantic hashing models.
no code implementations • 1 Sep 2023 • Jiatong Li, Qi Liu, Fei Wang, Jiayu Liu, Zhenya Huang, Fangzhou Yao, Linbo Zhu, Yu Su
However, we notice that this paradigm leads to the inevitable non-identifiability and explainability overfitting problem, which is harmful to the quantification of learners' cognitive states and the quality of web learning services.
no code implementations • 13 Jun 2023 • Vadim Zlotnikov, Jiayu Liu, Igor Halperin, Fei He, Lisa Huang
Crowding is widely regarded as one of the most important risk factors in designing portfolio strategies.
no code implementations • 11 Feb 2023 • Jiayu Liu, Zhenya Huang, ChengXiang Zhai, Qi Liu
In LeAp, we perform knowledge learning in a novel problem-knowledge-expression paradigm, with a Knowledge Encoder to acquire knowledge from problem data and a Knowledge Decoder to apply knowledge for expression reasoning.
no code implementations • 9 Feb 2023 • Yuting Ning, Jiayu Liu, Longhu Qin, Tong Xiao, Shangzi Xue, Zhenya Huang, Qi Liu, Enhong Chen, Jinze Wu
In the Natural Language for Optimization (NL4Opt) NeurIPS 2022 competition, competitors focus on improving the accessibility and usability of optimization solvers, with the aim of subtask 1: recognizing the semantic entities that correspond to the components of the optimization problem; subtask 2: generating formulations for the optimization problem.
1 code implementation • 20 Oct 2022 • Daniel LeJeune, Jiayu Liu, Reinhard Heckel
Machine learning systems are often applied to data that is drawn from a different distribution than the training distribution.
1 code implementation • 14 Apr 2022 • Mohammad Zalbagi Darestani, Jiayu Liu, Reinhard Heckel
We show that for four natural distribution shifts, this method essentially closes the distribution shift performance gap for state-of-the-art architectures for accelerated MRI.
no code implementations • 6 Jan 2022 • Igor Halperin, Jiayu Liu, Xiao Zhang
We suggest a simple practical method to combine the human and artificial intelligence to both learn best investment practices of fund managers, and provide recommendations to improve them.
no code implementations • 22 Jun 2020 • Jiayu Liu, Ioannis Chiotellis, Rudolph Triebel, Daniel Cremers
In active learning, sampling bias could pose a serious inconsistency problem and hinder the algorithm from finding the optimal hypothesis.
Ranked #108 on Image Classification on STL-10
no code implementations • 11 Dec 2019 • Jiayu Liu, Qiqi Zhang, Jiaxu Li, Ying Wang
The case studies indicate that the proposed method can determine radial topology in a few seconds and ensure the restoration capacity.