paper-with-me

Papers

Stochastic Aggregation in Graph Neural Networks

2021-02-25 · Yuanqing Wang, Theofanis Karaletsos

Graph neural networks (GNNs) manifest pathologies including over-smoothing and limited discriminating power as a result of suboptimally expressive aggregating mechanisms. We herein present a unifying framework for stochastic aggregation (STAG) in GNNs, where noise is (adaptively) injected into the aggregation process from the neighborhood to form node embeddings. We provide theoretical arguments that STAG models, with little overhead, remedy both of the aforementioned problems. In addition to fixed-noise models, we also propose probabilistic versions of STAG models and a variational inference framework to learn the noise posterior. We conduct illustrative experiments clearly targeting oversmoothing and multiset aggregation limitations. Furthermore, STAG enhances general performance of GNNs demonstrated by competitive performance in common citation and molecule graph benchmark datasets.

📄 PDF Abstract BibTeX arXiv:2102.12648

Code (1)

yuanqing-wang/stag 공식 구현 pytorch

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Policy Message Passing: A New Algorithm for Probabilistic Graph Inference

2019-09-29 · ICLR 2020 1 · Zhiwei Deng, Greg Mori

A general graph-structured neural network architecture operates on graphs through two core components: (1) complex enough message functions; (2) a fixed information aggregation process. In this paper, we present the Poli…

GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation

2022-03-02 · Sina Sajadmanesh, Ali Shahin Shamsabadi, Aurélien Bellet, Daniel Gatica-Perez

In this paper, we study the problem of learning Graph Neural Networks (GNNs) with Differential Privacy (DP). We propose a novel differentially private GNN based on Aggregation Perturbation (GAP), which adds stochastic no…

Node Classification

ABC: Aggregation before Communication, a Communication Reduction Framework for Distributed Graph Neural Network Training and Effective Partition

2022-12-11 · Junwei Su

Graph Neural Networks(GNNs) are a family of neural models tailored for graph-structure data and have shown superior performance in learning representations for graph-structured data. However, training GNNs on large graph…

Graph Neural Network

Robust Node Affinities via Jaccard-Biased Random Walks and Rank Aggregation

2026-03-05 · Bastian Pfeifer, Michael G. Schimek arxiv

Estimating node similarity is a fundamental task in network analysis and graph-based machine learning, with applications in clustering, community detection, classification, and recommendation. We propose TopKGraphs, a me…

Community Detection

Neighbor-Sampling Based Momentum Stochastic Methods for Training Graph Neural Networks

2025-08-01 · Molly Noel, Gabriel Mancino-Ball, Yangyang Xu arxiv

Graph convolutional networks (GCNs) are a powerful tool for graph representation learning. Due to the recursive neighborhood aggregations employed by GCNs, efficient training methods suffer from a lack of theoretical gua…

Graph Representation LearningNode Classification