Fetching the paper…

Reading the bibliography…

2019

Advancing GraphSAGE with A Data-Driven Node Sampling

Oh, Jihun, Cho, Kyunghyun, Bruna, Joan

Original
PDF
Post on X

Understand

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.

Advancing GraphSAGE with A Data-Driven Node Sampling · Around

Built on

Adam: A method for stochastic optimization
Original
Diederik P Kingma and Jimmy Ba · 2014
Earlier work this paper cites.
Node2Vec
Aditya Grover and Jure Leskovec · 2016
Earlier work this paper cites.
Semi-supervised classification with graph convolutional networks
Original
Thomas N Kipf and Max Welling · 2016
Earlier work this paper cites.
Neural Message Passing for Quantum Chemistry
Original
Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, and George E. Dahl · 2017
Earlier work this paper cites.

Similar

Inductive representation learning on large graphs
Will Hamilton, Zhitao Ying, and Jure Leskovec · 2017
Cited alongside, same era.
Neural message passing for jet physics
Isaac Henrion, Johann Brehmer, Joan Bruna, Kyunghyun Cho, Kyle Cranmer, Gilles Louppe, and Gaspar Rochette · 2017
Cited alongside, same era.
Column networks for collective classification
Trang Pham, Truyen Tran, Dinh Q Phung, and Svetha Venkatesh · 2017
Cited alongside, same era.
Graph attention networks
Original
Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio · 2017
Cited alongside, same era.

Then

Predicting multicellular function through multi-layer tissue networks
Marinka Zitnik and Jure Leskovec · 2017
Later among the works it cites.
Fastgcn: Fast Learning With Graph Convolu- Tional Networks Via Importance Sampling
Jie Chen, Tengfei Ma, and Cao Xiao · 2018
Later among the works it cites.
Graph neural networks for icecube signal classification
Nicholas Choma, Federico Monti, Lisa Gerhardt, Tomasz Palczewski, Zahra Ronaghi, Prabhat Prabhat, Wahid Bhimji, Michael Bronstein, Spencer Klein, and Joan Bruna · 2018
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…