Graph Convolutional Gaussian Processes
We propose a novel Bayesian nonparametric method to learn translation-invariant relationships on non-Euclidean domains. The resulting graph convolutional Gaussian processes can be applied to problems in machine learning for which the input observations are functions with domains on general graphs. The structure of these models allows for high dimensional inputs while retaining expressibility, as is the case with convolutional neural networks. We present applications of graph convolutional Gaussian processes to images and triangular meshes, demonstrating their versatility and effectiveness, comparing favorably to existing methods, despite being relatively simple models.
NurtureToken New!

Token crowdsale for this paper ends in

Buy Nurture Tokens

Authors

Are you an author of this paper? Check the Twitter handle we have for you is correct.

Ian Walker (edit)
Ben Glocker (add twitter)
Ask The Authors

Ask the authors of this paper a question or leave a comment.

Read it. Rate it.
#1. Which part of the paper did you read?

#2. The paper contains new data or analyses that is openly accessible?
#3. The conclusion is supported by the data and analyses?
#4. The conclusion is of scientific interest?
#5. The result is likely to lead to future research?

Github
User:
None (add)
Repo:
None (add)
Stargazers:
0
Forks:
0
Open Issues:
0
Network:
0
Subscribers:
0
Language:
None
Youtube
Link:
None (add)
Views:
0
Likes:
0
Dislikes:
0
Favorites:
0
Comments:
0
Other
Sample Sizes (N=):
Inserted:
Words Total:
Words Unique:
Source:
Abstract:
None
05/14/19 06:01PM
7,533
2,091
Tweets
arxiv_pop: 2019/05/14 投稿 5位 LG(Machine Learning) Graph Convolutional Gaussian Processes https://t.co/RcMRYLSkLn 7 Tweets 9 Retweets 52 Favorites
_Artemisa_v: RT @StatsPapers: Graph Convolutional Gaussian Processes. https://t.co/kWeZGKnT9x
arxiv_in_review: #ICML2019 Graph Convolutional Gaussian Processes. (arXiv:1905.05739v1 [cs\.LG]) https://t.co/YUhpYhHYnW
GlockerBen: Learning from non-Euclidean domains (graphs) with limited training data: Graph Convolutional Gaussian Processes by Ian Walker will be presented @icmlconf #icml2019. @BioMedIAICL @ICComputing With funding from @ERC_Research and @NERCscience Pre-print: https://t.co/b34FbTSOdk https://t.co/YQsDFciIlm
obedrios: RT @StatsPapers: Graph Convolutional Gaussian Processes. https://t.co/kWeZGKnT9x
arxiv_cscv: Graph Convolutional Gaussian Processes https://t.co/rJcgaEH3j5
SythonUK: RT @StatsPapers: Graph Convolutional Gaussian Processes. https://t.co/kWeZGKnT9x
JAdP: RT @StatsPapers: Graph Convolutional Gaussian Processes. https://t.co/kWeZGKnT9x
momijipan: RT @StatsPapers: Graph Convolutional Gaussian Processes. https://t.co/kWeZGKnT9x
ballforest: RT @StatsPapers: Graph Convolutional Gaussian Processes. https://t.co/kWeZGKnT9x
StatsPapers: Graph Convolutional Gaussian Processes. https://t.co/kWeZGKnT9x
arxiv_cs_LG: Graph Convolutional Gaussian Processes. Ian Walker and Ben Glocker https://t.co/jjIu0jKup4
BrundageBot: Graph Convolutional Gaussian Processes. Ian Walker and Ben Glocker https://t.co/66NDAjmr5o
Images
Related