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, disrupting the structural bias in graphs, and having limited improvement on oversquashing in terms of oversquashing measure. Motivated by unitary RNN, we propose Graph Unitary Message Passing (GUMP) to alleviate oversquashing in GNNs by applying unitary adjacency matrix for message passing. To design GUMP, a transformation is first proposed to make general graphs have unitary adjacency matrix and keep its structural bias. Then, unitary adjacency matrix is obtained with a unitary projection algorithm, which is implemented by utilizing the intrinsic structure of unitary adjacency matrix and allows GUMP to be permutation-equivariant. Experimental results show the effectiveness of GUMP in improving the performance on various graph learning tasks.

📄 PDF Abstract BibTeX arXiv:2403.11199

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Learning

A Unitary Transform Based Generalized Approximate Message Passing

2022-10-17 · Jiang Zhu, Xiangming Meng, Xupeng Lei, Qinghua Guo

We consider the problem of recovering an unknown signal ${\mathbf x}\in {\mathbb R}^n$ from general nonlinear measurements obtained through a generalized linear model (GLM), i.e., ${\mathbf y}= f\left({\mathbf A}{\mathbf…

compressed sensing

Unitary Approximate Message Passing for Matrix Factorization

2022-07-31 · Zhengdao Yuan, Qinghua Guo, Yonina C. Eldar, Yonghui Li

We consider matrix factorization (MF) with certain constraints, which finds wide applications in various areas. Leveraging variational inference (VI) and unitary approximate message passing (UAMP), we develop a Bayesian …

Compressive Sensing Dictionary Learning Variational Inference

Unitary convolutions for learning on graphs and groups

2024-10-07 · Bobak T. Kiani, Lukas Fesser, Melanie Weber

Data with geometric structure is ubiquitous in machine learning often arising from fundamental symmetries in a domain, such as permutation-invariance in graphs and translation-invariance in images. Group-convolutional ar…

Inductive Bias

Unitary Approximate Message Passing for Sparse Bayesian Learning

2021-01-25 · Man Luo, Qinghua Guo, Ming Jin, Yonina C. Eldar 외

Sparse Bayesian learning (SBL) can be implemented with low complexity based on the approximate message passing (AMP) algorithm. However, it does not work well for a generic measurement matrix, which may cause AMP to dive…

Variational Inference

Sensing Aided Uplink Transmission in OTFS ISAC with Joint Parameter Association, Channel Estimation and Signal Detection

2023-05-19 · Xi Yang, Hang Li, Qinghua Guo, J. Andrew Zhang 외

In this work, we study sensing-aided uplink transmission in an integrated sensing and communication (ISAC) vehicular network with the use of orthogonal time frequency space (OTFS) modulation. To exploit sensing parameter…

Integrated sensing and communication ISAC