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. By viewing the framelet-based models as discretized gradient flows of some energy, we show it can induce both low-frequency and high-frequency-dominated dynamics, via the separate weight matrices for different frequency components. This substantiates its good empirical performance on both homophilic and heterophilic graphs. We then propose a generalized energy via framelet decomposition and show its gradient flow leads to a novel graph neural network, which includes many existing models as special cases. We then explain how the proposed model generally leads to more flexible dynamics, thus potentially enhancing the representation power of graph neural networks.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph Neural NetworkSimilar Papers 제목 키워드 기반
Revisiting Generalized p-Laplacian Regularized Framelet GCNs: Convergence, Energy Dynamic and Training with Non-Linear Diffusion
This paper presents a comprehensive theoretical analysis of the graph p-Laplacian regularized framelet network (pL-UFG) to establish a solid understanding of its properties. We conduct a convergence analysis on pL-UFG, a…
Graph Neural NetworkData-Adaptive Graph Framelets with Generalized Vanishing Moments for Graph Signal Processing
In this paper, we propose a novel and general framework to construct tight framelet systems on graphs with localized supports based on hierarchical partitions. Our construction provides parametrized graph framelet system…
DenoisingGradient Flow of Energy: A General and Efficient Approach for Entity Alignment Decoding
Entity alignment (EA), a pivotal process in integrating multi-source Knowledge Graphs (KGs), seeks to identify equivalent entity pairs across these graphs. Most existing approaches regard EA as a graph representation lea…
Entity AlignmentEntity EmbeddingsGraph Representation LearningKnowledge Graphs+3Adaptive directional Haar tight framelets on bounded domains for digraph signal representations
Based on hierarchical partitions, we provide the construction of Haar-type tight framelets on any compact set $K\subseteq \mathbb{R}^d$. In particular, on the unit block $[0,1]^d$, such tight framelets can be built to be…
Permutation Equivariant Graph Framelets for Heterophilous Graph Learning
The nature of heterophilous graphs is significantly different from that of homophilous graphs, which causes difficulties in early graph neural network models and suggests aggregations beyond the 1-hop neighborhood. In th…
Graph LearningGraph Neural Network