Advancing GraphSAGE with A Data-Driven Node Sampling

2019-04-29 · Jihun Oh, Kyunghyun Cho, Joan Bruna

As an efficient and scalable graph neural network, GraphSAGE has enabled an inductive capability for inferring unseen nodes or graphs by aggregating subsampled local neighborhoods and by learning in a mini-batch gradient descent fashion. The neighborhood sampling used in GraphSAGE is effective in order to improve computing and memory efficiency when inferring a batch of target nodes with diverse degrees in parallel. Despite this advantage, the default uniform sampling suffers from high variance in training and inference, leading to sub-optimum accuracy. We propose a new data-driven sampling approach to reason about the real-valued importance of a neighborhood by a non-linear regressor, and to use the value as a criterion for subsampling neighborhoods. The regressor is learned using a value-based reinforcement learning. The implied importance for each combination of vertex and neighborhood is inductively extracted from the negative classification loss output of GraphSAGE. As a result, in an inductive node classification benchmark using three datasets, our method enhanced the baseline using the uniform sampling, outperforming recent variants of a graph neural network in accuracy.

📄 PDF Abstract BibTeX arXiv:1904.12935

Code (1)

oj9040/GraphSAGE_RL 공식 구현 tf

Tasks

General Classification Graph Neural Network Node Classification Reinforcement Learning

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음

GraphSAGE GraphSAGE is a general inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen…

Cooperative Causal GraphSAGE

2025-05-20 · Zaifa Xue, Tao Zhang, Tuo Xu, Huaixin Liang 외

GraphSAGE is a widely used graph neural network. The introduction of causal inference has improved its robust performance and named as Causal GraphSAGE. However, Causal GraphSAGE focuses on measuring causal weighting amo…

Causal Inference Graph Neural Network

DistGNN-MB: Distributed Large-Scale Graph Neural Network Training on x86 via Minibatch Sampling

2022-11-11 · Md Vasimuddin, Ramanarayan Mohanty, Sanchit Misra, Sasikanth Avancha

Training Graph Neural Networks, on graphs containing billions of vertices and edges, at scale using minibatch sampling poses a key challenge: strong-scaling graphs and training examples results in lower compute and highe…

Graph Neural Network

BIGSAGE: unsupervised inductive representation learning of graph via bi-attended sampling and global-biased aggregating

2019-05-01 · ICLR 2019 5 · Xin Luo, Hankz Hankui Zhuo

Different kinds of representation learning techniques on graph have shown significant effect in downstream machine learning tasks. Recently, in order to inductively learn representations for graph structures that is unob…

Representation Learning Transfer Learning

Soybean Disease Detection via Interpretable Hybrid CNN-GNN: Integrating MobileNetV2 and GraphSAGE with Cross-Modal Attention

2025-03-03 · Md Abrar Jahin, Soudeep Shahriar, M. F. Mridha, Md. Jakir Hossen 외

Soybean leaf disease detection is critical for agricultural productivity but faces challenges due to visually similar symptoms and limited interpretability in conventional methods. While Convolutional Neural Networks (CN…

Computational Efficiency Graph Neural Network

Towards Graph-Based Deep Learning for Map Generalization: Insights from Building Footprints Simplification and Aggregation

2026-06-18 · Yanning Wang, Zhiyong Zhou, Zhouyu Liu, Mengni Yu 외 arxiv

Map generalization remains one of the fundamental tasks in cartography, especially for the simplification and aggregation of complex building footprints. This study presents the first exploratory application of graph-bas…

Graph Neural Network Link Prediction Graph Learning