Skip to content

berges99/GNN-Extrapolation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

51 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

The Simplicity Bias of Graph Neural Networks

Explain general purpose of the work...

Data

Synthetic Data

Explain generate_synthetic_data.py and the structure of the datasets.

Datasets

Explain download_data.{py,sh} and the downloadable datasets.

Node Representations

Distances

Teacher Setting

The teacher setting ...

python3 run_teacher.py --dataset_filename ) [DATASET_FILENAME]
                       --initial_relabeling ) {'ones', 'degrees'}
                       # -v | --verbose ) [VERBOSE]
                       # --save_file_destination ) [SAVE_FILE_DESTINATION]
                       --num_iterations ) [NUM_ITERATIONS]
                       --setting ) {'regression', 'classification'}
                       --classes ) [CLASSES]
                       --bias ) [BIAS]
                       --lower_bound ) [LOWER_BOUND]
                       --upper_bound ) [UPPER_BOUND]
                       {'GIN'} ...

Commented arguments are mostly used for internal development. After all the optional arguments, one must specify the GNN model as a positional argument, followed by all its specific arguments detailed in previous sections. For more information on the arguments, types and descriptions, run python3 run_teacher.py --help.

Student Setting

The student setting ...

python3 run_model.py --

TBD


Available Models

TBD

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages