1.6k citations
- Tsinghua UniversityCN16 papers
- Chinese Academy of SciencesCN15 papers
- Xi'an Jiaotong UniversityCN15 papers
- Ministry of Industry and Information TechnologyCN14 papers
- Xidian UniversityCN12 papers
- Australian National UniversityAU11 papers
- Moscow Institute of Physics and TechnologyRU11 papers
- University of Chinese Academy of SciencesCN10 papers
- Nankai UniversityCN9 papers
- Fudan UniversityCN7 papers
- Instituto de Ciencia de Materiales de MadridES7 papers
- The University of AdelaideAU7 papers
25 papers · 1 filter
Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning
Chenjia Bai, Lingxiao Wang, Jianye Hao +4
Offline Reinforcement Learning (RL) has shown promising results in learning a task-specific policy from a fixed dataset. However, successful offline RL often relies heavily on the…
Deep Contrastive Graph Learning with Clustering-Oriented Guidance
Mulin Chen, Bocheng Wang, Xuelong Li
Graph Convolutional Network (GCN) has exhibited remarkable potential in improving graph-based clustering. To handle the general clustering scenario without a prior graph, these mod…
A Novel Normalized-Cut Solver with Nearest Neighbor Hierarchical Initialization
Feiping Nie, Jitao Lu, Danyang Wu +2
Normalized-Cut (N-Cut) is a famous model of spectral clustering. The traditional N-Cut solvers are two-stage: 1) calculating the continuous spectral embedding of normalized Laplaci…
Comprehensive evaluation of deep and graph learning on drug-drug interactions prediction
Xuan Lin, Lichang Dai, Yafang Zhou +9
Recent advances and achievements of artificial intelligence (AI) as well as deep and graph learning models have established their usefulness in biomedical applications, especially…
Data-driven prognostics based on time-frequency analysis and symbolic recurrent neural network for fuel cells under dynamic load
Chu Wang, Manfeng Dou, Zhongliang Li +6
Data-centric prognostics is beneficial to improve the reliability and safety of proton exchange membrane fuel cell (PEMFC). For the prognostics of PEMFC operating under dynamic loa…
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning
Xuelong Li, Hongyuan Zhang, Rui Zhang
The existing matrix completion methods focus on optimizing the relaxation of rank function such as nuclear norm, Schatten-p norm, etc. They usually need many iterations to converge…