paper-with-me

Papers

Convolutional Networks on Enhanced Message-Passing Graph Improve Semi-Supervised Classification with Few Labels

2021-09-29 · Yu Song, Shan Lu, Dehong Qiu

Efficient message propagation is critical to node classification in sparse graph with few labels that remains largely unaddressed until now. Recently popularized Graph Convolutional Networks (GCNs) lack the ability to propagate message to distant nodes because of over-smoothing. Besides, GCNs with numerous parameters suffer from overfitting when labeled nodes are scarce. We attack this problem via building GCNs on Enhanced Message-Passing Graph (EMPG). The key idea is node classification can benefit from various variants of the original graph that are more efficient for message propagation, based upon the assumption that each variant is a potential structure as more nodes are properly labeled. Specifically, we first map nodes to a latent space through graph embedding that captures structure information. Considering node attributes together, we construct EMPG by adding connections between nodes in close proximity in the latent space. With the help of added connections, EMPG allows a node to propagate message to the right nodes at distance, so that GCNs on EMPG need not stack multiple layers and therefore avoid over-smoothing. However, adding connections may cause message propagation saturation or lead to overfitting. Seeing EMPG as an accumulation of the potential variants of the original graph, we apply dropout to EMPG and train GCNs on various dropout graphs. The features learned from different dropout EMPGs are aggregated to compute the final prediction. Experiments demonstrate a significant improvement on node classification in sparse graph with few labels.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Graph EmbeddingNode Classification

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Language Model-Enhanced Message Passing for Heterophilic Graph Learning

2025-05-26 · Wenjun Wang, Dawei Cheng

Traditional graph neural networks (GNNs), which rely on homophily-driven message passing, struggle with heterophilic graphs where connected nodes exhibit dissimilar features and different labels. While existing methods a…

Active LearningGraph LearningLanguage ModelingLanguage Modelling

Concept Graph Convolutions: Message Passing in the Concept Space

2026-04-22 · Lucie Charlotte Magister, Pietro Lio arxiv

The trust in the predictions of Graph Neural Networks is limited by their opaque reasoning process. Prior methods have tried to explain graph networks via concept-based explanations extracted from the latent representati…

Convergence of Message Passing Graph Neural Networks with Generic Aggregation On Large Random Graphs

2023-04-21 · Matthieu Cordonnier, Nicolas Keriven, Nicolas Tremblay, Samuel Vaiter

We study the convergence of message passing graph neural networks on random graph models to their continuous counterpart as the number of nodes tends to infinity. Until now, this convergence was only known for architectu…

Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction

2023-11-29 · Xinshun Wang, Wanying Zhang, Can Wang, Yuan Gao 외

Graph Convolutional Networks (GCN) which typically follows a neural message passing framework to model dependencies among skeletal joints has achieved high success in skeleton-based human motion prediction task. Neverthe…

Human motion predictionmotion prediction

EEGNN: Edge Enhanced Graph Neural Network with a Bayesian Nonparametric Graph Model

2022-08-12 · Yirui Liu, Xinghao Qiao, Liying Wang, Jessica Lam

Training deep graph neural networks (GNNs) poses a challenging task, as the performance of GNNs may suffer from the number of hidden message-passing layers. The literature has focused on the proposals of {over-smoothing}…

Graph Neural Network