3.7k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Chinese Academy of SciencesCN257 papers
- Beijing Academy of Quantum Information SciencesCN235 papers
- Peking UniversityCN220 papers
- University of Science and Technology of ChinaCN204 papers
- Tsinghua UniversityCN193 papers
- University of Chinese Academy of SciencesCN143 papers
- University of Hong KongHK135 papers
- Institute of PhysicsPL94 papers
- National University of SingaporeSG94 papers
- Peng Cheng LaboratoryCN94 papers
- Hong Kong University of Science and TechnologyHK93 papers
- Fudan UniversityCN90 papers
13 papers · 2 filters
A Survey on Neural Network Interpretability
Yu Zhang, Peter Tiňo, Aleš Leonardis +1
Along with the great success of deep neural networks, there is also growing concern about their black-box nature. The interpretability issue affects people's trust on deep learning…
Deep-learning based discovery of partial differential equations in integral form from sparse and noisy data
Hao Xu, Dongxiao Zhang, Nanzhe Wang
Data-driven discovery of partial differential equations (PDEs) has attracted increasing attention in recent years. Although significant progress has been made, certain unresolved i…
Theory-guided Auto-Encoder for Surrogate Construction and Inverse Modeling
Nanzhe Wang, Haibin Chang, Dongxiao Zhang
A Theory-guided Auto-Encoder (TgAE) framework is proposed for surrogate construction and is further used for uncertainty quantification and inverse modeling tasks. The framework is…
Bigeminal Priors Variational auto-encoder
Xuming Ran, Mingkun Xu, Qi Xu +2
Variational auto-encoders (VAEs) are an influential and generally-used class of likelihood-based generative models in unsupervised learning. The likelihood-based generative models…
Weak Form Theory-guided Neural Network (TgNN-wf) for Deep Learning of Subsurface Single and Two-phase Flow
Rui Xu, Dongxiao Zhang, Miao Rong +1
Deep neural networks (DNNs) are widely used as surrogate models in geophysical applications; incorporating theoretical guidance into DNNs has improved the generalizability. However…
A Lagrangian Dual-based Theory-guided Deep Neural Network
Miao Rong, Dongxiao Zhang, Nanzhe Wang
The theory-guided neural network (TgNN) is a kind of method which improves the effectiveness and efficiency of neural network architectures by incorporating scientific knowledge or…
A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton
Risheng Liu, Pan Mu, Xiaoming Yuan +2
In recent years, a variety of gradient-based first-order methods have been developed to solve bi-level optimization problems for learning applications. However, theoretical guarant…
Detecting Out-of-distribution Samples via Variational Auto-encoder with Reliable Uncertainty Estimation
Xuming Ran, Mingkun Xu, Lingrui Mei +2
Variational autoencoders (VAEs) are influential generative models with rich representation capabilities from the deep neural network architecture and Bayesian method. However, VAE…
Rotation-Equivariant Neural Networks for Privacy Protection
Hao Zhang, Yiting Chen, Haotian Ma +5
In order to prevent leaking input information from intermediate-layer features, this paper proposes a method to revise the traditional neural network into the rotation-equivariant…
Privacy-preserving Traffic Flow Prediction: A Federated Learning Approach
Yi Liu, James J. Q. Yu, Jiawen Kang +2
Existing traffic flow forecasting approaches by deep learning models achieve excellent success based on a large volume of datasets gathered by governments and organizations. Howeve…
Ternary Compression for Communication-Efficient Federated Learning
Jinjin Xu, Wenli Du, Ran Cheng +2
Learning over massive data stored in different locations is essential in many real-world applications. However, sharing data is full of challenges due to the increasing demands of…
HOTCAKE: Higher Order Tucker Articulated Kernels for Deeper CNN Compression
Rui Lin, Ching-Yun Ko, Zhuolun He +5
The emerging edge computing has promoted immense interests in compacting a neural network without sacrificing much accuracy. In this regard, low-rank tensor decomposition constitut…
Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs
Han Yang, Xiao Yan, Xinyan Dai +2
Graph neural networks (GNNs) have received much attention recently because of their excellent performance on graph-based tasks. However, existing research on GNNs focuses on design…