How mostly-ai/paper-tabular-argn works
This repository is a research artifact for the TabularARGN paper: it provides training datasets, scripts for generating synthetic tabular data with TabularARGN and comparison methods, and generated outputs. The principal workflow is a researcher running a method script on training data and saving synthetic datasets. The excerpts show flat and relational generation separately. Source connections below are limited to sampled scripts; the README identifies the paper and points to the reference implementation in another repository, which is outside this tree.
Main entry points: data_train Training data · data_synthetic Generated datasets · run_tabARGN.py TabularARGN flat · script_tabARGN_california.py TabularARGN relational
Components 15
Input datasets
- Training data
data_train
Flat generation
- TabularARGN flat
scripts_flat/run_tabARGN.py - Flat baselines
scripts_flat/run_baselines_flat.py
Relational generation
- TabularARGN relational
scripts_sequential/script_tabARGN_california.py - TabularARGN baseball
scripts_sequential/script_tabARGN_baseball.py - RCTGAN
scripts_sequential/script_rctgan_california.py - RCTGAN baseball
scripts_sequential/script_rctgan_baseball.py - REaLTabFormer
scripts_sequential/script_rtf_california.py - REaLTabFormer baseball
scripts_sequential/script_rtf_baseball.py - SDV HMA
scripts_sequential/script_sdv_hma_california.py - SDV HMA baseball
scripts_sequential/script_sdv_hma_baseball.py - SDV PAR
scripts_sequential/script_sdv_par_california.py - SDV PAR baseball
scripts_sequential/script_sdv_par_baseball.py
Synthetic outputs
- Generated datasets
data_synthetic
Other components
- Researcher
Connections 35
- Researcher → TabularARGN flat: runs
scripts_flat/run_tabARGN.py - Researcher → Flat baselines: runs
scripts_flat/run_baselines_flat.py - Researcher → TabularARGN relational: runs
scripts_sequential/script_tabARGN_california.py - Researcher → TabularARGN baseball: runs
scripts_sequential/script_tabARGN_baseball.py - Researcher → RCTGAN: runs
scripts_sequential/script_rctgan_california.py - Researcher → RCTGAN baseball: runs
scripts_sequential/script_rctgan_baseball.py - Researcher → REaLTabFormer: runs
scripts_sequential/script_rtf_california.py - Researcher → REaLTabFormer baseball: runs
scripts_sequential/script_rtf_baseball.py - Researcher → SDV HMA: runs
scripts_sequential/script_sdv_hma_california.py - Researcher → SDV HMA baseball: runs
scripts_sequential/script_sdv_hma_baseball.py - Researcher → SDV PAR: runs
scripts_sequential/script_sdv_par_california.py - Researcher → SDV PAR baseball: runs
scripts_sequential/script_sdv_par_baseball.py - TabularARGN flat → Training data: reads
scripts_flat/run_tabARGN.py - Flat baselines → Training data: preprocesses
scripts_flat/run_baselines_flat.py - TabularARGN relational → Training data: reads
scripts_sequential/script_tabARGN_california.py - TabularARGN baseball → Training data: reads
scripts_sequential/script_tabARGN_baseball.py - RCTGAN → Training data: reads
scripts_sequential/script_rctgan_california.py - RCTGAN baseball → Training data: reads
scripts_sequential/script_rctgan_baseball.py - REaLTabFormer → Training data: reads
scripts_sequential/script_rtf_california.py - REaLTabFormer baseball → Training data: reads
scripts_sequential/script_rtf_baseball.py - SDV HMA → Training data: reads
scripts_sequential/script_sdv_hma_california.py - SDV HMA baseball → Training data: reads
scripts_sequential/script_sdv_hma_baseball.py - SDV PAR → Training data: reads
scripts_sequential/script_sdv_par_california.py - SDV PAR baseball → Training data: reads
scripts_sequential/script_sdv_par_baseball.py - TabularARGN flat → Generated datasets: writes
scripts_flat/run_tabARGN.py - TabularARGN relational → Generated datasets: writes
scripts_sequential/script_tabARGN_california.py - TabularARGN baseball → Generated datasets: writes
scripts_sequential/script_tabARGN_baseball.py - RCTGAN → Generated datasets: writes
scripts_sequential/script_rctgan_california.py - RCTGAN baseball → Generated datasets: writes
scripts_sequential/script_rctgan_baseball.py - REaLTabFormer → Generated datasets: writes
scripts_sequential/script_rtf_california.py - REaLTabFormer baseball → Generated datasets: writes
scripts_sequential/script_rtf_baseball.py - SDV HMA → Generated datasets: writes
scripts_sequential/script_sdv_hma_california.py - SDV HMA baseball → Generated datasets: writes
scripts_sequential/script_sdv_hma_baseball.py - SDV PAR → Generated datasets: writes
scripts_sequential/script_sdv_par_california.py - SDV PAR baseball → Generated datasets: writes
scripts_sequential/script_sdv_par_baseball.py