MarkovGNN: Graph Neural Networks on Markov Diffusion
Most real-world networks contain well-defined community structures where nodes are densely connected internally within communities. To learn from these networks, we develop MarkovGNN that captures the formation and evolution of communities directly in different convolutional layers. Unlike most Graph Neural Networks (GNNs) that consider a static graph at every layer, MarkovGNN generates different stochastic matrices using a Markov process and then uses these community-capturing matrices in different layers. MarkovGNN is a general approach that could be used with most existing GNNs. We experimentally show that MarkovGNN outperforms other GNNs for clustering, node classification, and visualization tasks. The source code of MarkovGNN is publicly available at \url{https://github.com/HipGraph/MarkovGNN}.
Code (1)
Tasks
ClusteringNode ClassificationSimilar Papers 제목 키워드 기반
A Markov Variation Approach to Smooth Graph Signal Interpolation
In this paper we present the Markov variation, a smoothness measure which offers a probabilistic interpretation of graph signal smoothness. This measure is then used to develop an optimization framework for graph signal …
Diffusion Maps for Signal Filtering in Graph Learning
This paper explores the application diffusion maps as graph shift operators in understanding the underlying geometry of graph signals. The study evaluates the improvements in graph learning when using diffusion map gener…
Graph LearningLocality Preserving Markovian Transition for Instance Retrieval
Diffusion-based re-ranking methods are effective in modeling the data manifolds through similarity propagation in affinity graphs. However, positive signals tend to diminish over several steps away from the source, reduc…
Re-RankingRetrievalMeasuring Spatial Clustering via Metropolis-Hastings Diffusion Distance
We propose a novel measure of the discrepancy between two probability distributions $f$ and $g$ on a graph - which we call the diffusion distance - that measures the rate of convergence of $f$ to $g$ under a graph-constr…
MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering
Graph Neural Networks (GNNs) have recently been utilized to build Collaborative Filtering (CF) models to predict user preferences based on historical user-item interactions. However, there is relatively little understand…
Collaborative FilteringMulti-modal RecommendationRecommendation SystemsRepresentation Learning