Search Results for author:
Found 9 papers, 2 papers with code
AdaptGear: Accelerating GNN Training via Adaptive Subgraph-Level Kernels on GPUs
Graph neural networks (GNNs) are powerful tools for exploring and learning from graph structures and features.
Frequency Pooling: Shift-Equivalent and Anti-Aliasing Downsampling
We prove that frequency pooling is shift-equivalent and anti-aliasing based on the property of Fourier transform and Nyquist frequency.
Learning Multi-Layered GBDT Via Back Propagation
In this paper, we propose a framework of learning multi-layered GBDT via BP.
Frequency Pooling: Shift-Equivalent and Anti-Aliasing Down Sampling
Convolutional layer utilizes the shift-equivalent prior of images which makes it a great success for image processing.
GBDT-MO: Gradient Boosted Decision Trees for Multiple Outputs
When there are multiple outputs, GBDT constructs multiple trees corresponding to the output variables.
Adversarial Defense by Suppressing High-frequency Components
Recent works show that deep neural networks trained on image classification dataset bias towards textures.
Recurrent Convolution for Compact and Cost-Adjustable Neural Networks: An Empirical Study
However, the performance of an RC network is not satisfactory if we directly unroll the same kernels multiple steps.
Recurrent Convolutions: A Model Compression Point of View
RC reduces the redundancy across layers and is complementary to most existing model compression approaches.
Regularization Neural Networks via Constrained Virtual Movement Field
We define the approximated smoothness as the regularization term.
