2022 Developer Survey is open! Take survey.

Questions tagged [graph-neural-networks]

For questions related to graph neural networks, which are artificial neural networks applied to graphs.

Filter by
Sorted by
Tagged with
0 votes
0 answers
14 views

Can GNNs be used to predict the performance of a Neural Network?

Is possible to use a GNN to learn the hyperparameters and structure of a given DNN program (Tensorflow or PyTorch) and predict some metric about the program (accuracy, etc). Apparently, all PyTorch ...
user avatar
0 votes
1 answer
41 views

How to understand the GCN equation?

I understand GCN does message passing with its neighbours to learn the node embedding. But I don't understand the following equation. What "tilda" is referring to equation ...
user avatar
0 votes
0 answers
24 views

How does Weight Sharing with the Generalization in Graph Neural Networks work?

I have two closely related points regarding the weight sharing and generalization of graph Neural network. For illustration purposes, I attached two images which I reference. Images are taken from the ...
user avatar
  • 101
0 votes
0 answers
23 views

What is SE(3) transformer and what does RoseTTAFold use it for?

As is mentioned in its paper, the SE(3) transformer is a kind of self-attention-based structure that guarantees SE(3)-equivariance. So what is the reason that RoseTTAFold uses it and what for?
user avatar
  • 101
0 votes
0 answers
21 views

What are attention heads in a Graph Attention Layers

I am using the EGATConv layer for an edge classification task. One of the constructor's parameters is num_heads, which is number of attention heads. I can't really ...
user avatar
1 vote
0 answers
15 views

In Graph Neural Network is Message Passing Step Agnostic of Output Values during Training?

So Graph Neural Networks is about representation learning where initially representation of graph is learned in the form of node embeddings. My question is: Are the output values back propagated and ...
user avatar
  • 135
0 votes
0 answers
10 views

Does having more edges on a GNN helps learning?

I am doing a machine translation task using a Graph2Seq graph neutral network. I am using GAT as my encoder. Graph stats: I have around 400 nodes in the graph per data point. In the current graph, on ...
user avatar
0 votes
0 answers
18 views

Papers or reviews of Heterogeneous Graph Neural Networks [closed]

I am looking for papers that work on heterogeneous graphs, in the sense that we have 2 types of nodes with different feature sets and 3 types of edges also with different feature sets across the ...
user avatar
  • 101
0 votes
1 answer
45 views

What is the best GNN for a NMT task?

I am doing a machine translation task using a Graph2Seq graph neutral network. There are many different variants of GNN: GCN GAT GraphSage GGNN Which one would be the most effective for a machine ...
user avatar
0 votes
0 answers
11 views

How can I prove "If the canonical forms of two graphs are not equivalent, then the graphs are definitively not isomorphic." on WL-test?

WL-Test is used for checking whether two graphs are isomorphic or not. It can make a graph to a canonical form. How can I prove that if canonical forms of two graphs are different, then they are non-...
user avatar
  • 115
1 vote
1 answer
61 views

How to use structural information in a Transformer?

I am performing a Neural Machine Translation (NMT) task. In my case, input data has relational information. I know I can use a Graph Neural Network (GNN) and use a Graph2Seq model. But I can't find a ...
user avatar
1 vote
1 answer
32 views

What kind of features does each node have as an input graph to a graph neural network?

What kind of features does each node have as an input graph to a graph neural network? For example, we want to do image classification with GNN, what are the features of each pixel? Or if anyone could ...
user avatar
  • 11
1 vote
1 answer
56 views

Is "node embedding" in GNN analogous to "hidden layer" of FFN?

So in Graph Neural Network (GNN) we have node embeddings which is a feature vector that describes the node, is it analogous to hidden layer of Artificial neural network such as feed-forward neural ...
user avatar
  • 135
1 vote
0 answers
18 views

How to model graph node as priority list over a visual scene in neuro-symbolic AI?

Suppose if we have a visual scene graph and we model each component in the scene as a node of a graph and edges which are relationship between the visual scene components. Some of the nodes are like ...
user avatar
  • 21
0 votes
0 answers
23 views

Temporal Graph Neural Network for motion prediction

Temporal Graph Neural Networks have been used for motion prediction (or traffic forecasting) in the following recent papers: Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion ...
user avatar
0 votes
0 answers
28 views

How can I verify two graphs are isomorphic or not with GNN?

I have read How powerful are Graph Neural Networks, Xu et al. , and I got a question. How can I compare a pair of graphs? I know that graph classification is to classify graphs to some groups. However,...
user avatar
  • 115
1 vote
0 answers
28 views

Graph Neural Networks: Why do papers use very low label rates?

I was recently reading the following paper: "Semi-supervised classification with Graph Convolutional Networks" by Kipf and Welling (here). Question: When testing on datasets, why are the ...
user avatar
2 votes
0 answers
66 views

What is the difference between Probabilistic Graphical models and Graph Neural networks?

While going over PGMs and GNNs, it seems like both leverage the graph data structure. The former has been used to represent causal associations (among other things), while the latter has a varied set ...
user avatar
0 votes
0 answers
116 views

Why is the Graph Isomorphism Network powerful?

I am reading a paper known as GIN, How powerful are graph neural networks?, Xu et al. 2019 The paper, Lemma 5 and Corollary 6, introduces Graph Isomorphism Network (GIN). In Lemma 5, Moreover, any ...
user avatar
  • 115
1 vote
1 answer
137 views

What is a filter in the context of graph convolutional networks?

In Section 2.1 of the research paper titled Semi-Supervised Classification with Graph Convolutional Networks by Thomas N. Kipf et al., Spectral convolution on graphs defined as The multiplication of ...
user avatar
  • 115
1 vote
1 answer
147 views

How are GCN doing semi-supervised learning?

In Semi-Supervised Classification with Graph Convolutional Networks, the authors say that GCN is an approach for semi-supervised learning (SSL). But a GCN is making predictions using only the graph ...
user avatar
1 vote
1 answer
33 views

Graph Convolutional Networks: why are non-parametric filters not localized in space?

I was reading the following paper here about some of the groundwork in graph deep learning. On page 3, in the bit entitled Polynomial parameterization for localized filters, it states that non-...
user avatar
0 votes
0 answers
17 views

Why is/can node classification (graph machine learning) be semi-supervised while graph classification is supervised?

I was reading about different graph machine learning tasks in this book (Chapter 1) here and to learn about node classification and graph classification tasks. Then I looked at this paper here, which ...
user avatar
1 vote
1 answer
125 views

How do graph neural networks adapt to different number of nodes and connections of different graphs?

I have recently been studying GNN, and the fundamental idea seems to be the aggregation and transfer of information from a node's neighborhood to update the node's internal state. However, there are ...
user avatar
  • 123
0 votes
0 answers
17 views

Why does conditioning neural network function on adjacency matrix of graph allow for distribution of gradient information from the supervised loss?

I was reading the following paper here and had a question about the paragraph on page 1 (in the introduction). The equation being referred to is: $$ \mathcal{L} = \mathcal{L}_0 + \lambda \mathcal{L}_{\...
user avatar
0 votes
0 answers
14 views

How to initialize the coefficient vector of Deep Tensor Neural Network

In Quantum-Chemical Insights from Deep Tensor Neural Networks, I would like to ask a question about how to initialize the coefficient vector of the network, because I could not understand it even ...
user avatar
0 votes
1 answer
93 views

Does the Weisfeiler-Lehman Isomorphism Test end?

I am studying GNNs. I am interested in the Weisfeiler-Lehman Isomorphism Test (WL-Test). I was looking for information about whether the test always ends or not, but I didn't find a definitive answer. ...
user avatar
  • 115
1 vote
0 answers
17 views

What is the reason behind using node embeddings?

I was reading Chapter 3 from the following book (here) on graph representation learning. The chapter is about node embeddings. Question: What is the point of using node embeddings? Do we use them: to ...
user avatar
2 votes
0 answers
33 views

What are examples of node 'features' in graph networks?

Context: I was reading Chapter 3 in the following book (here) about graph representation learning. Before I get to node embeddings, I wanted to make sure that I do understand what is meant by the ...
user avatar
0 votes
0 answers
20 views

How does graph Fourier transform work when multiple signals present on each node?

Context: I was reading the following set of notes (page 83): here and it says: Thus, the Fourier transform of signal (or function) $ \mathbf{f} \in R^{|V|} $ on a graph can be computed as $$ \mathbf{...
user avatar
0 votes
0 answers
90 views

How does Chebyshev approximation of spectral convolution work?

I was reading the following paper: here. In it, it talks about spectral graph convolutions and says: We consider spectral convolutions on graphs defined as the multiplication of a signal $x \in R^N$ (...
user avatar
1 vote
1 answer
102 views

How do convolutional layers of basic Graph Convolutional Networks work?

I was reading the following article on Towards Data Science (here) and it says the following, regarding the calculation of convolutional layers: So the overall steps are: Transform the graph into ...
user avatar
0 votes
0 answers
19 views

Question about eigenvectors of Laplacian matrix in relation to graph Fourier transform?

(I have copied this question from my post on maths stack exchange as I don't think it was getting much/any traction there) I am reading the following book/notes on Graph Representation Learning (here) ...
user avatar
1 vote
2 answers
66 views

Can I extend Graph Convolutional Networks to graphs with weighted edges?

I'm researching spatio-temporal forecasting utilising GCN as a side project, and I am wondering if I can extend it by using a graph with weighted edges instead of a simple adjacency matrix with 1's ...
user avatar
1 vote
1 answer
44 views

Why does $I_N + D^{-\frac{1}{2}}AD^{-\frac{1}{2}}$ have eigenvalues in the range [0, 2]?

In Semi-supervised classification with Graph Convolutional Networks, I am unable to understand a few things. Given an undirected graph having adjacency matrix $A$, degree matrix $D_{ii} = \sum_j A_{...
user avatar
0 votes
0 answers
30 views

Graph neural network - what level (node or link or graph) prediction should be used for my problem?

I posted this on cross-validated but did not get a response. Trying my luck here. Sorry if this is not recommended. I have an undirected graph with nodes separated within a specified distance, say d, ...
user avatar
  • 1
1 vote
0 answers
18 views

Is graph embedding linear in its maintaining of graph geometry?

It is claimed that the main goal of graph embedding methods is to pack every node's properties into a vector with a smaller dimension, so node similarity in the original complex irregular spaces can ...
user avatar
  • 251
0 votes
0 answers
25 views

Are there any good references that describe the equations of the forward pass of Graph Neural Networks?

I am trying to program Graph Neural Network from scratch. Can the community please suggest a good reference/s to read about the equations of the forward pass in Graph Neural Networks, especially in ...
user avatar
  • 121
2 votes
0 answers
87 views

Are spectral approaches to Graph Neural Networks still considered?

I've been reading several papers and reviews about Graph Neural Networks, and I still feel a bit confused about the difference between the two approaches, and also if the spatial approaches have ...
user avatar
0 votes
0 answers
15 views

How exactly is masking performed in the training part of the paper "Semi-Supervised Classification with Graph Convolutional Networks"?

I am struggling to understand the training part of the paper Semi-Supervised Classification with Graph Convolutional Networks (2017) by Thomas Kipf and Max Welling. The GitHub repo is here. I do not ...
user avatar
0 votes
0 answers
27 views

Which well known node embedding algorithms to use for weighted graphs?

I am looking for a node representation learning algorithm to generate node embeddings that supports weighted graphs. I modified GCN to support weighted graphs, but I want to know an algorithm that ...
user avatar
1 vote
1 answer
29 views

Why the non-exploitation of edge labels in current graph convolutions "results in an overly homogeneous view of local graph neighborhoods"?

I am currently reading a paper called Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs (2017, CPPR), and I cannot understand the following sentence: We identify that the ...
user avatar
2 votes
1 answer
487 views

How does the K-dimensional WL test work?

I am reading a paper on the K-WL GCN. I did not complete the paper yet, but I just skimmed over it. There I am trying to understand the K-WL test (page 3 Weisfeiler-Leman Algorithm). I think my ...
user avatar
1 vote
1 answer
128 views

Is there a graph neural network algorithm that can deal with a different number of input and output nodes?

I am new to graph neural networks and their applications. I have an input graph $G = \{V, E\}$ and an output graph $G' = \{V', E'\}$ where the number of nodes $V$ and $V'$ are different. I am trying ...
user avatar
  • 133
2 votes
0 answers
72 views

Reinforcement learning and Graph Neural Networks: Entropy drops to zero

I am currently working on an experiment to link reinforcement learning with graph neural networks. This is my architecture: Feature Extraction with GCN: there is a fully meshed topology with ...
user avatar
0 votes
0 answers
25 views

How to deal with dynamically changing input tensor in neural networks without padding?

I have a dataset about the monitored health/growth of a community of people. The dataset has tensor shaped (batch_size, features, person, window), where: person==...
user avatar
2 votes
0 answers
42 views

Given a 2-layer GCN, can we choose the dimensions of the 2nd weight matrix, such that this architecture has the same capacity as a 1-layer GCN?

This might be more of a question about nested function classes: For $k$ class node classification in a graph with $n$ nodes, and $d$ feature vector. I want to compare Architecture I: the GCN model of ...
user avatar
  • 121
3 votes
1 answer
213 views

Are Graph Neural Networks generalizations of Convolutional Neural Networks?

In lecture 4 of this course, the instructor argues that GNNs are generalizations of CNNs, and that one can recover CNNs from GNNs. He presents the following diagram (on the right) and mentions that it ...
user avatar
1 vote
0 answers
28 views

Spectral Networks and Deep Locally Connected Networks on Graphs

I’m reading the paper Spectral Networks and Deep Locally Connected Networks on Graphs and I’m having a hard time understanding the notation shown in the picture below (the scribbles are mine): ...
user avatar
3 votes
1 answer
162 views

How can we derive a Convolution Neural Network from a more generic Graph Neural Network?

Convolution Neural Network (CNNs) operate over strict grid-like structures ($M \times N \times C$ images), whereas Graph Neural Networks (GNNs) can operate over all-flexible graphs, with an undefined ...
user avatar
  • 39