paper-with-me

홈 › Papers

A Feedforward Unitary Equivariant Neural Network

2022-08-25 · Pui-Wai Ma, T. -H. Hubert Chan

We devise a new type of feedforward neural network. It is equivariant with respect to the unitary group $U(n)$. The input and output can be vectors in $\mathbb{C}^n$ with arbitrary dimension $n$. No convolution layer is required in our implementation. We avoid errors due to truncated higher order terms in Fourier-like transformation. The implementation of each layer can be done efficiently using simple calculations. As a proof of concept, we have given empirical results on the prediction of the dynamics of atomic motion to demonstrate the practicality of our approach.

📄 PDF Abstract BibTeX arXiv:2208.12146

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Activation Functions for "A Feedforward Unitary Equivariant Neural Network"

2024-11-17 · Pui-Wai Ma

In our previous work [Ma and Chan (2023)], we presented a feedforward unitary equivariant neural network. We proposed three distinct activation functions tailored for this network: a softsign function with a small residu…

Form

Precoder Learning by Leveraging Unitary Equivariance Property

2025-03-12 · Yilun Ge, Shuyao Liao, Shengqian Han, Chenyang Yang

Incorporating mathematical properties of a wireless policy to be learned into the design of deep neural networks (DNNs) is effective for enhancing learning efficiency. Multi-user precoding policy in multi-antenna system,…

Graph Unitary Message Passing

2024-03-17 · Haiquan Qiu, Yatao Bian, Quanming Yao

Message passing mechanism contributes to the success of GNNs in various applications, but also brings the oversquashing problem. Recent works combat oversquashing by improving the graph spectrums with rewiring techniques…

Graph Learning

Optimization Dynamics of Equivariant and Augmented Neural Networks

2023-03-23 · Oskar Nordenfors, Fredrik Ohlsson, Axel Flinth

We investigate the optimization of neural networks on symmetric data, and compare the strategy of constraining the architecture to be equivariant to that of using data augmentation. Our analysis reveals that that the rel…

Data Augmentation

Smoothness Errors in Dynamics Models and How to Avoid Them

2026-02-05 · Edward Berman, Luisa Li, Jung Yeon Park, Robin Walters arxiv

Modern neural networks have shown promise for solving partial differential equations over surfaces, often by discretizing the surface as a mesh and learning with a mesh-aware graph neural network. However, graph neural n…

Graph Neural NetworkWeather Forecasting