Questions tagged [geometric-deep-learning]

For questions related to geometric deep learning, which is the application of deep learning techniques to non-Euclidean data (e.g. graphs and manifolds).

Filter by
Sorted by
Tagged with
2
votes
0answers
67 views

Why can we perform graph convolution using the standard 2d convolution with $1 \times \Gamma$ kernels?

Recently I was reading this paper Skeleton Based Action RecognitionUsing Spatio Temporal Graph Convolution. In this paper, the authors claim (below equation (\ref{9})) that we can perform graph ...
1
vote
0answers
51 views

Can I think graph convolution as 2D convolution like images?

Kipf et al described in his paper that we can write graph convolution operation like this: $$H_{t+1} = AH_tW_t$$ where, $A$ is the normalized adjacency matrix, $H_t$ is the embedded representation of ...
1
vote
1answer
51 views

How Graph Convolutional Neural Networks forward propagate?

In the basic variant of GCN we have the following formulation: Here we aggregate the information from adjacent node and pass it to a neural network, then transform our own information and add them ...
2
votes
0answers
43 views

What is the best resources to learn Graph Convolutional Neural Networks?

For the past few days, I am trying to learn graph convolutional networks. I saw some of the lectures on youtube. But I can not able to get any clear concept of how those networks are trained. I have a ...
1
vote
0answers
18 views

How to design a graph neural network to predict the forces in truss elements of a space frame?

I am trying to create a Graph NN that will be able to predict the forces in truss elements of a space frame. The input for the NN will be a graph, where the nodes represent the nodes of the spaceframe....
1
vote
0answers
17 views

How do CNNs or RNNs “stack the feature of nodes by a specific order”?

I am trying to understand the following statement taken from the paper Graph Neural Networks: A Review of Methods and Applications (2019). Standard neural networks like CNNs and RNNs cannot handle ...
2
votes
1answer
41 views

Understanding the node information score in the paper “Hierarchical Graph Pooling with Structure Learning”

The paper Hierarchical Graph Pooling with Structure Learning (2019) introduces a distance measure between: a graph's node-representation matrix $\text{H}$, and an approximation of this constructed ...
1
vote
1answer
35 views

What are some conferences for publishing papers on graph convolutional networks?

What are some conferences for publishing papers on graph convolutional networks?
1
vote
0answers
15 views

How to estimate the convolutional representation of a graph from its similarity to other graph convolutional representation?

Suppose we have two graphs A and B disconnected to each other (let's say 2-hops each), within a larger graph. If the convolutional representation of graph A is known, is it possible to estimate the ...
2
votes
0answers
16 views

How should I deal with multi-dimensional tensors for nodes in a graph convolution network?

How to work with GCN when the features of each node is not a 1D vector? For example, if the graph has N nodes and each node has features of the form $C \times D \times E$. Also, is there an open-...
3
votes
1answer
67 views

How can I learn a graph given nodes with features in a supervised fashion?

I have a dataset and want to be able to construct a graph from it in a supervised fashion. Let's assume I have a dataset with N nodes, each node has e.g. 10 features. Out of these N nodes, I want to ...
2
votes
0answers
43 views

Suitable deep learning algorithms for spatial / geometric data

I have a task of classifying spatial data from a geographic information system. More precisely, I need a way to filter out unnecessary line segments from the CAD system before loading into the GIS (...
1
vote
0answers
24 views

Which generative methods are better for generating graphs, while preserving node and edge labels?

I started to dig into the topic of graph generation and I have a question - which out of generative methods (autoregressive, variational autoencoders, GANs, any other?) are better for generating ...
1
vote
0answers
42 views

Can GraphRNN be used with very large graphs?

In the GraphRNN paper, the authors only implement the algorithm up to a graph size of 2k nodes. Would this still work on much larger graphs (on the order of $10^7$)? Or would the computation just ...
3
votes
2answers
60 views

How to represent and work with the feature matrix for graph convolutional network (GCN) if the number of features for each node is different?

I have a question regarding features representation for graph convolutional neural network. For my case, all nodes have a different number of features, and for now, I don't really understand how ...
2
votes
1answer
36 views

What is the difference between graph semi-supervised learning and normal semi-supervised learning?

Whenever I look for papers involving semi-supervised learning, I always find some that talk about graph semi-supervised learning (e.g. A Unified Framework for Data Poisoning Attack to Graph-based Semi-...
3
votes
0answers
31 views

Creating an AI than can learn to give instructions

So we think a computer is dumb because it can only follow instructions. Therefor I am trying to create an AI that can give instructions. The idea is this: Create a geometric scene (A) then make a ...
2
votes
0answers
58 views

How should I handle different input sizes in graph convolution networks?

I'm a student beginning to study deep learning, and would like to practice with a simple project using a Graph Convolutional Network. However, I'm not quite sure how to handle different input sizes ...
4
votes
2answers
84 views

Is there an open-source implementation for graph convolution networks for weighted graphs?

Currently, I'm using a Python library, StellarGraph, to implement GCN. And I now have a situation where I have graphs with weighted edges. Unfortunately, StellarGraph doesn't support those graphs I'm ...
3
votes
1answer
158 views

Is there any Python library available for manifold learning using diffusion map? [closed]

I would like to use unsupervised learning with a technique called diffusion map based manifold learning in Python. The original paper on the diffusion map is An Introduction to Diffusion Maps. I have ...
1
vote
0answers
11 views

Is there any time-varying directed graph dataset?

I am interested in the node classification task for graph data. So far,I've tried it with the Cora dataset, but it is an undirected graph and has word attributes as features. I want to extend this ...
4
votes
1answer
50 views

What are the exact meaning of “lower-order structure” and “higher-order structure” in this paper?

I recently read a paper on community detection in networks. In the paper EdMot: An Edge Enhancement Approach for Motif-aware Community Detection, the authors consider the "lower-order structure" of ...
7
votes
2answers
1k views

What is the difference between graph convolution in the spatial vs spectral domain?

I've been reading different papers regarding graph convolution and it seems that they come into two flavors: spatial and spectral. From what I can see the main difference between the two approaches is ...
2
votes
1answer
78 views

How are edge features implemented in Geometric Deep Learning?

The work I've seen so far have the nodes containing features. Any resources for how to use a GCN on a graph where the edges are the ones that contain features rather than the nodes?
2
votes
1answer
76 views

Does GraphSage use hard attention?

I was reading the recent paper Graph Representation Learning via Hard and Channel-Wise Attention Networks, where the authors claim that there is no hard attention operator for graph data. From my ...
1
vote
0answers
29 views

What are the advantages of time-varying graph CNNs compared to fixed graph?

As I wrote in the title, what are the advantages of time-varying graph CNNs compared to fixed graph? For example, in CORA, which is a graph of citation relations of papers frequently used in graph CNN,...
2
votes
1answer
111 views

Is there a neural network method for time-varying directed graphs?

I want to study NN for time-varying directed graphs. However, as this field has developed relatively recently, it is difficult to find new ways. So the question is, is there any NN that can handle ...
2
votes
0answers
72 views

Why is graph convolution network in time-varying graphs useful for anomaly detection?

In this paper, the authors refer to the application of time-varying graphs as an open problem. And they say it will be useful for anomaly detection in financial networks, etc. But why is that useful?
3
votes
1answer
56 views

Examples of time-varying graph-structured data in real world

I'm looking for examples of time-varying graph-structured data for time-varying graph CNNs. First, I came up with the idea of infection network. Is there anything more? If possible, I want data that ...
2
votes
0answers
23 views

Random graph as input in geometric deep learning on time-varying graph

I want to create a framework that allows GDL to be applied to time-varying graphs. I came up with the Erdos-renyi model as an example of a time-varying graphs. GDL for graphs takes node information ...
1
vote
2answers
96 views

What are the differences between network analysis and geometric deep learning on graphs?

Both of them deal with data of graph structure like a network community. Is there a big difference there?
3
votes
0answers
37 views

What are the benefits of using the state information that maintains the graph structure?

When you applying a graph structured data to the graph convolution network, what are the benefits of using the state information that maintains the graph structure?
3
votes
1answer
60 views

What is the purpose and benefit of applying CNN to a graph?

I'm new to the graph convolution network. I wonder what is the main purpose of applying data with graph structure to CNN?
4
votes
0answers
238 views

What is the difference between GAT and GaAN?

I was looking at two papers Graph Attention Networks (GAT) by Petar Veličković and GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs by Jiani Zhang. I'm trying to ...
3
votes
2answers
121 views

Are there neural networks that accept graphs or trees as inputs?

As far I know, the RNN accepts a sequence as input and can produce as a sequence as output. Are there neural networks that accept graphs or trees as inputs, so that to represent the relationships ...
5
votes
1answer
92 views

Do you know any examples of geometric deep learning used in industry?

I'm interested in the industrial use of GDL (see https://arxiv.org/abs/1611.08097). Is it used in industry? That is, does any company have access to non-Euclidean data and process it directly instead ...
2
votes
0answers
39 views

Should I use the hyperbolic distance loss in the case of Poincarè Disk Model?

I trained a neural network which makes a regression to a Poincarè Disk Model with radius $r = 1$. I want to optimize using the hyperbolic distance $$ \operatorname{arcosh} \left( 1 + \frac{2|pq|^2|...
6
votes
3answers
4k views

What is non-Euclidean data?

What is non-Euclidean data? Where does this type of data arises? Apparently, graphs and manifolds are non-Euclidean data. Why exactly is that the case? What is the difference between non-Euclidean and ...
4
votes
1answer
226 views

What is a graph neural network?

What is a graph neural network (GNN)? How is a GNN different from a NN? How exactly is a GNN related to graphs? What are the components of a GNN? What are the inputs and outputs of GNNs? How can ...
11
votes
2answers
2k views

What is geometric deep learning?

What is geometric deep learning (GDL)? How is it different from deep learning? Why do we need GDL? What are some applications of GDL?
9
votes
2answers
754 views

What benefits can be got by applying Graph Convolutional Neural Network instead of ordinary CNN?

What benefits can we got by applying Graph Convolutional Neural Network instead of ordinary CNN? I mean if we can solve a problem by CNN, what is the reason should we convert to Graph Convolutional ...