jhljx / ctgcn Goto Github PK
View Code? Open in Web Editor NEWCTGCN: k-core based Temporal Graph Convolutional Network for Dynamic Graphs (accepted by IEEE TKDE in 2020) https://ieeexplore.ieee.org/document/9240056
License: MIT License
CTGCN: k-core based Temporal Graph Convolutional Network for Dynamic Graphs (accepted by IEEE TKDE in 2020) https://ieeexplore.ieee.org/document/9240056
License: MIT License
Hello, @jhljx. First of all I want to thank you for the great work you put in this OS project.
Trying the VGRNN code found an error at line 497 in baseline/VGRNN.py. When concatenating phi_x_t and h[-1] there is a mismatch: phi_x_t is of size (num_nodes x hidden) and h[-1] is size (input_features x hidden_dim), so that joining them on dim=1 results in an error, unless you have input_features == num_nodes, which is the case when you're very lucky or do not have node_features and they're initialized as an Identity of size num_nodes x num_nodes, which is the base case you support.
Have you considered this case and I'm doing something wrong or you didn't provided support for this? Thanks in advance.
I want to know that sometimes the programe can generate walk pairs, sometimes it can't as the walk pairs floder has nothing. The programe can't call the function helper.random_walk.
Hi, I have learnt a lot from your codes.
But when I run the link prediction task with 'python3 main.py --config=config/uci.json --task=embedding --method=CTGCN-S', I met the error:
ValueError: Output size (199,) is not compatible with broadcast dimensions of inputs (1, 199).
I also met the same error when trying the methods 'CGCN-S' and 'EvolveGCN'.
Learn a lot! I met this question.
It is that if I need to divide train.csv, valid.csv,and test.csv by myself.
I see that original dataset does not have following folders.
FileNotFoundError: [Errno 2] File /data/uci/lp_data_0/2004-05_train.csv does not exist: '/data/uci/lp_data_0/2004-05_train.csv'
Thank you
It seems you always use 1-core adj?
Since all your CoreDiffusion
layers use core_num
default value 1..
CoreDiffusion(input_dim, output_dim, bias=bias, rnn_type=rnn_type)
If so, how k-core works?
Hi, your work is very meaningful.
But I have some problems, I am performing a dynamic graph embedding algorithm(DynGEM) on my own undirected weighted graph dataset and the loss function cannot converge.
So, are these dynamic graph embedding algorithms suitable for undirected weighted graph datasets?
Thanks in advance for your answer!
Hi! Thanks for the great repository. I am using your approach to do link prediction on a dataset and this dataset has a lot of nodes, it has near 60000 nodes and 4 million edges. However, I cannot run your approach or other approaches like DynGEM or VGRNN on this dataset because it ran into CUDA OOM. The only approaches which worked for me from this repository are the GCRN and TIMERS.
I am wondering whether there is something I can tune in the config files so I can run the code successfully on my gpu without CUDA OOM. I have tried reducing the hidden_dims
and batch_size
but no luck. It seems not to change anything at all. I even tried batch_size
of 1 and hidden_dims
of 1.
Would you mind giving me some suggestions about that?
Thanks a lot in advance!
Hi,
After attempting to run the Graph Embedding example: python3 main.py --config=config/uci.json --task=embedding --method=CTGCN-C
, I receive an error stating that there is no such file or directory leading to the path: /CTGCN/data/uci/CTGCN/ctgcn_cores
. I noticed it is optional in the uci.json config file, so after removing it I get yet another error stating: TypeError: expected str, bytes or os.PathLike object, not NoneType
from line 57 in the helper.py
file.
I was wondering if the folder: ctgcn_cores is missing from the repository, and if there is another way around this issue.
Thanks
miss pair file. CTGCN/data/europe_air/CTGCN/gcn_walk_pairs
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.