Add resource "How powerful are Graph Convolutional Networks?" Accepted
Changes: 9
-
Add Graph convolutional networks
- Title
-
- Unchanged
- Graph convolutional networks
- Type
-
- Unchanged
- Blog post
- Created
-
- Unchanged
- 2016-09-30
- Description
-
- Unchanged
- Many important real-world datasets come in the form of graphs or networks: social networks, knowledge graphs, protein-interaction networks, the World Wide Web, etc. (just to name a few). Yet, until recently, very little attention has been devoted to the generalization of neural network models to such structured datasets. In the last couple of years, a number of papers re-visited this problem of generalizing neural networks to work on arbitrarily structured graphs (Bruna et al., ICLR 2014; Henaff et al., 2015; Duvenaud et al., NIPS 2015; Li et al., ICLR 2016; Defferrard et al., NIPS 2016; Kipf & Welling, ICLR 2017), some of them now achieving very promising results in domains that have previously been dominated by, e.g., kernel-based methods, graph-based regularization techniques and others. In this post, I will give a brief overview of recent developments in this field and point out strengths and drawbacks of various approaches.
- Link
-
- Unchanged
- http://tkipf.github.io/graph-convolutional-networks/
- Identifier
-
- Unchanged
- no value
Resource | v1 | current (v1) -
Add How powerful are Graph Convolutions? (review of Kipf & Welling, 2016)
- Title
-
- Unchanged
- How powerful are Graph Convolutions? (review of Kipf & Welling, 2016)
- Type
-
- Unchanged
- Blog post
- Created
-
- Unchanged
- 2016-09-13
- Description
-
- Unchanged
- This post is about a paper that has just come out recently on practical generalizations of convolutional layers to graphs: Thomas N. Kipf and Max Welling (2016) Semi-Supervised Classification with Graph Convolutional Networks Along the way I found this earlier, related paper: Defferrard, Bresson and Vandergheynst (NIPS 2016) Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering This post is mainly a review of (Kipf and Welling, 2016). The paper is nice to read, and while I like the general idea, I feel like the approximations made in the paper are too limiting and severely hurt the generality of the models we can build. This post explains why.
- Link
-
- Unchanged
- https://www.inference.vc/how-powerful-are-graph-convolutions-review-of-kipf-welling-2016-2/
- Identifier
-
- Unchanged
- no value
Resource | v1 | current (v1) -
Add Geometric Deep Learning
- Title
-
- Unchanged
- Geometric Deep Learning
- Type
-
- Unchanged
- Hub
- Created
-
- Unchanged
- no value
- Description
-
- Unchanged
- This website represents a collection of materials in the field of Geometric Deep Learning. We collect workshops, tutorials, publications and code, that several differet researchers has produced in the last years. Our goal is to provide a general picture of this new and emerging field, which is rapidly developing in the scientific community, thanks to the broad applicability it presents.
- Link
-
- Unchanged
- http://geometricdeeplearning.com/
- Identifier
-
- Unchanged
- no value
Resource | v1 | current (v1) -
Add Graph convolutional networks (GCN)
- Title
-
- Unchanged
- Graph convolutional networks (GCN)
- Description
-
- Unchanged
- Generalization of neural networks to arbitrary graphs.
- Link
-
- Unchanged
- no value
Topic | v1 | current (v1) -
Add Graph convolutional networks (GCN) treated in Graph convolutional networks
- Current
- treated in
Topic to resource relation | v1 -
Add Graph convolutional networks (GCN) cons given in How powerful are Graph Convolutions? (review of Kipf & Welling, 2016)
- Current
- cons given in
Topic to resource relation | v1 -
Add Graph convolutional networks (GCN) treated in Geometric Deep Learning
- Current
- treated in
Topic to resource relation | v1 -
Add Deep learning parent of Graph convolutional networks (GCN)
- Current
- (detached)
Topic to topic relation | v1 -
Add Graph convolutional networks reviewed in How powerful are Graph Convolutions? (review of Kipf & Welling, 2016)
- Current
- reviewed in
Resource to resource relation | v1