GeniePath: Graph Neural Networks with Adaptive Receptive Paths

02/03/2018
by   Ziqi Liu, et al.
0

We present, GeniePath, a scalable approach for learning adaptive receptive fields of neural networks defined on permutation invariant graph data. In GeniePath, we propose an adaptive path layer consists of two functions designed for breadth and depth exploration respectively, where the former learns the importance of different sized neighborhoods, while the latter extracts and filters signals aggregated from neighbors of different hops away. Our method works both in transductive and inductive settings, and extensive experiments compared with state-of-the-art methods show that our approaches are useful especially on large graph.

READ FULL TEXT
research
01/29/2022

Rewiring with Positional Encodings for Graph Neural Networks

Several recent works use positional encodings to extend the receptive fi...
research
08/05/2017

Depth Adaptive Deep Neural Network for Semantic Segmentation

In this work, we present the depth-adaptive deep neural network using a ...
research
04/21/2020

PAI-GCN: Permutable Anisotropic Graph Convolutional Networks for 3D Shape Representation Learning

Demand for efficient 3D shape representation learning is increasing in m...
research
07/16/2023

Automated Polynomial Filter Learning for Graph Neural Networks

Polynomial graph filters have been widely used as guiding principles in ...
research
01/02/2019

Measuring Physical Activity of Older Adults via Smartwatch and Stigmergic Receptive Fields

Physical activity level (PAL) in older adults can enhance healthy aging,...
research
03/29/2021

RAN-GNNs: breaking the capacity limits of graph neural networks

Graph neural networks have become a staple in problems addressing learni...
research
05/10/2023

Towards Scalable Adaptive Learning with Graph Neural Networks and Reinforcement Learning

Adaptive learning is an area of educational technology that consists in ...

Please sign up or login with your details

Forgot password? Click here to reset