Yu Guang Wang
8 papers · 2020–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15) 🐣 Hot Topic Early Bird
❓
The Questioner
Venues
Top co-authors
Research topics
Deep Learning
(8)
Architectures
(8)
Machine Learning
(6)
Core Methods
(5)
Artificial Intelligence
(3)
Core AI
(3)
Computer Science
(1)
Computer Vision
(1)
Analysis
(1)
Applications
(1)
Learning Types
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Techniques
(1)
Keywords
graph neural network
(4)
graph classification
(2)
graph pooling
(2)
message passing
(2)
graph convolution
(1)
neural ordinary differential equation
(1)
trajectory prediction
(1)
shallow neural network
(1)
wavelet analysis
(1)
weight matrix
(1)
approximation theory
(1)
random neural network
(1)
geometric transformation
(1)
graph fourier transform
(1)
multi-resolution analysis
(1)
haar wavelet
(1)
motion prediction
(1)
node classification
(1)
spectral transformation
(1)
wavelet transform
(1)
Papers
Limiting Over-Smoothing and Over-Squashing of Graph Message Passing by Deep Scattering Transforms
JMLR 2026
How Universal Polynomial Bases Enhance Spectral Graph Neural Networks: Heterophily, Over-smoothing, and Over-squashing
ICML 2024
ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks
ICLR 2023
EqMotion: Equivariant Multi-Agent Motion Prediction With Invariant Interaction Reasoning
CVPR 2023
How Powerful are Shallow Neural Networks with Bandlimited Random Weights?
ICML 2023
Decimated Framelet System on Graphs and Fast G-Framelet Transforms
JMLR 2022
Haar Graph Pooling
ICML 2020
Path Integral Based Convolution and Pooling for Graph Neural Networks
NeurIPS 2020