Questions tagged [graphs]
For the nodes and links sense of graph; use the visualization tag for the charting sense.
226 questions
2
votes
0
answers
44
views
Any latency focused graph databases?
I’m a developer and data scientist working with large graph datasets (multi-million nodes/edges) in production pipelines.
Currently I’m using Neo4j, but as graph size and query depth increase, I’m ...
1
vote
0
answers
48
views
Combining Embeddings and Ontology (DAG) in Visualisation
How can I visualise a hierarchical ontology of items in embedding space, combining text embeddings with the graphical structure? (Something similar to the example below)
I have a hierarchical ...
3
votes
1
answer
85
views
Is it possible to make the python widget in Orange to give output and receive input (both in the same widget)
I'm working on a project which works on loop control, when I try to implement that in the orange platform, I'm unable to connect one widget (python script) to another in loop, as the connection is ...
3
votes
1
answer
56
views
Is a bipartite graph count as knowledge graph?
I make a graph about costumer, but it is a bipartite graph, each customer doesn't related to other customer? Is that counts as Knowledge graph?
0
votes
0
answers
29
views
How to use graph convolutional neural network (GCNN) to predict the appropriate patterns to solve an scheduling problem
I am working on a scheduling problem where I am willing to solve that by Graph Convolutional Neural Network (GCNN). The problem is stated as follows:
There is an assembly product graph with $\text{G(V,...
2
votes
0
answers
50
views
Need help with model architecture and sampling negative edges
I am currently training a graph transformer model in order to develop an AI who'd be able to generate edges on a unseen graph (link dependencies between text with historical data).
I divided my ...
1
vote
0
answers
30
views
Preference learning for collaborative scheduling
I am working on a project of integrating the preferences of the workers into a schedule, I mean we won’t only satisfy the systematic constraints but also users preferences as constraints, so we are ...
2
votes
0
answers
38
views
Ultra-Minimalist Visualization for Term Frequency Table (Alternative for Tag Cloud)
Disclaimer: I have no background in Data Science or Statistics.
I used AI to extract a vast list of topical keywords, from thousands of news articles, published by dozens of Tech News Publications, ...
0
votes
0
answers
51
views
Is my Pytorch's LSTM underfiting
Friends here I want to ask about graph loss on my LSTM Pytorch modeling for stock price prediction, with like this is my modeling overfitting? for the results themselves are good, like this:
MSE: ...
1
vote
0
answers
27
views
Triplet extraction in german domain-specific text documents
I'm look for a solution to extract triplets from german domain-specific documents for knowledge graph construction. The documents combines law and physics. There is restriction, that only allows local ...
2
votes
0
answers
43
views
Machine learning with one graph per record
I have a set of 100k graphs G, each graph has an associated result y (float).
Each graph contains 10 to 10000 nodes.
Each node has 2 to 20 directional edges and 6 categorical attributes.
I have this ...
0
votes
0
answers
36
views
Given the total cost of a graph walk, how to estimate the cost of each edge?
I have a real-world problem in which I have a collection of nodes and their edges. This collection is composed of hundreds of nodes and thousands of connections. Then I have about 10 K datapoints each ...
1
vote
0
answers
61
views
How to Interpret Laplacian Scores for Feature Importance Ranking in Unsupervised Feature Clustering?
I am currently working on unsupervised feature importance ranking using graph clustering methods, specifically focusing on the Laplacian score as a metric. However, I am struggling to clarify the ...
1
vote
1
answer
56
views
How to Visualize a PyTorch Model Without Input Parameters?
I’m working on a project that heavily relies on computation graph manipulations but isn’t directly in the field of machine learning. However, we are using PyTorch due to its flexibility and support ...
0
votes
2
answers
166
views
Clique partition for an undirected weighted graph
I have an undirected graph and graph edges are weighted. I want to partition the graph into cliques. I don't know the number of cliques in advance.
These are the objectives:
Primary objective: The ...