Search Results for author:
Found 14 papers, 5 papers with code
Design Your Own Universe: A Physics-Informed Agnostic Method for Enhancing Graph Neural Networks
Physics-informed Graph Neural Networks have achieved remarkable performance in learning through graph-structured data by mitigating common GNN challenges such as over-smoothing, over-squashing, and heterophily adaption.
SpecSTG: A Fast Spectral Diffusion Framework for Probabilistic Spatio-Temporal Traffic Forecasting
Our method generates the Fourier representation of future time series, transforming the learning process into the spectral domain enriched with spatial information.
TransNeXt: Robust Foveal Visual Perception for Vision Transformers
Due to the depth degradation effect in residual connections, many efficient Vision Transformers models that rely on stacking layers for information exchange often fail to form sufficient information mixing, leading to unnatural visual perception.
Ranked #15 on
Domain Generalization
on ImageNet-A
Exposition on over-squashing problem on GNNs: Current Methods, Benchmarks and Challenges
Graph-based message-passing neural networks (MPNNs) have achieved remarkable success in both node and graph-level learning tasks.
From Continuous Dynamics to Graph Neural Networks: Neural Diffusion and Beyond
Such a scheme has been found to be intrinsically linked to a physical process known as heat diffusion, where the propagation of GNNs naturally corresponds to the evolution of heat density.
Bregman Graph Neural Network
Numerous recent research on graph neural networks (GNNs) has focused on formulating GNN architectures as an optimization problem with the smoothness assumption.
Ranked #31 on
Node Classification
on Texas
Unifying over-smoothing and over-squashing in graph neural networks: A physics informed approach and beyond
To explore more flexible filtering conditions, we further generalize MHKG into a model termed G-MHKG and thoroughly show the roles of each element in controlling over-smoothing, over-squashing and expressive power.
How Curvature Enhance the Adaptation Power of Framelet GCNs
Motivated by the geometric analogy of Ricci curvature in the graph setting, we prove that by inserting the curvature information with different carefully designed transformation function $\zeta$, several known computational issues in GNN such as over-smoothing can be alleviated in our proposed model.
Frameless Graph Knowledge Distillation
Knowledge distillation (KD) has shown great potential for transferring knowledge from a complex teacher model to a simple student model in which the heavy learning task can be accomplished efficiently and without losing too much prediction accuracy.
Revisiting Generalized p-Laplacian Regularized Framelet GCNs: Convergence, Energy Dynamic and Training with Non-Linear Diffusion
We conduct a convergence analysis on pL-UFG, addressing the gap in the understanding of its asymptotic behaviors.
Generalized Laplacian Regularized Framelet Graph Neural Networks
This paper introduces a novel Framelet Graph approach based on p-Laplacian GNN.
Generalized energy and gradient flow via graph framelets
In this work, we provide a theoretical understanding of the framelet-based graph neural networks through the perspective of energy gradient flow.
A Discussion On the Validity of Manifold Learning
In this work, we investigate the validity of learning results of some widely used DR and ManL methods through the chart mapping function of a manifold.
Coupling Matrix Manifolds and Their Applications in Optimal Transport
These geometrical features of CMM have paved the way for developing numerical Riemannian optimization algorithms such as Riemannian gradient descent and Riemannian trust-region algorithms, forming a uniform optimization method for all types of OT problems.
