{"id":15882777,"url":"https://github.com/chris-santiago/met","last_synced_at":"2025-10-07T00:37:00.119Z","repository":{"id":211938840,"uuid":"727032806","full_name":"chris-santiago/met","owner":"chris-santiago","description":"Reproducing the MET framework with PyTorch","archived":false,"fork":false,"pushed_at":"2023-12-13T04:37:48.000Z","size":11469,"stargazers_count":4,"open_issues_count":1,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-07-20T03:09:56.236Z","etag":null,"topics":["adversarial-learning","hydra","masked-autoencoder","pytorch","pytorch-lightning","self-supervised-learning","taskfile","transformers"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/chris-santiago.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-12-04T03:23:00.000Z","updated_at":"2025-01-28T14:39:57.000Z","dependencies_parsed_at":"2023-12-11T18:38:13.181Z","dependency_job_id":null,"html_url":"https://github.com/chris-santiago/met","commit_stats":null,"previous_names":["chris-santiago/met"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/chris-santiago/met","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chris-santiago%2Fmet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chris-santiago%2Fmet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chris-santiago%2Fmet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chris-santiago%2Fmet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/chris-santiago","download_url":"https://codeload.github.com/chris-santiago/met/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chris-santiago%2Fmet/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267605942,"owners_count":24114618,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-07-28T02:00:09.689Z","response_time":68,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["adversarial-learning","hydra","masked-autoencoder","pytorch","pytorch-lightning","self-supervised-learning","taskfile","transformers"],"created_at":"2024-10-06T04:07:07.252Z","updated_at":"2025-10-07T00:36:55.097Z","avatar_url":"https://github.com/chris-santiago.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MET - PyTorch\n\nThis repo reproduces the MET (Masked Encoding for Tabular Data) framework for self-supervised learning with tabular data.\n\n*Authors: Kushal Majmundar, Sachin Goyal, Praneeth Netrapalli, Prateek Jain*\n\n*Reference: Kushal Majmundar, Sachin Goyal, Praneeth Netrapalli, Prateek Jain, \"MET: Masked Encoding for Tabular Data,\" Neural Information Processing Systems (NeurIPS), 2022.*\n\nOriginal paper: https://table-representation-learning.github.io/assets/papers/met_masked_encoding_for_tabula.pdf\n\nOriginal repo: https://github.com/google-research/met\n\n## Install\n\nClone this repository, create a new Conda environment and \n\n```bash\ngit clone https://github.com/chris-santiago/met.git\nconda env create -f environment.yml\ncd met\npip install -e .\n```\n\n## Use\n\n### Prerequisites\n\n#### Hydra\n\nThis project uses [Hydra](https://hydra.cc/docs/intro/) for managing configuration CLI arguments. See `met/conf` for full\nconfiguration details.\n\n#### Task\n\nThis project uses [Task](https://taskfile.dev/) as a task runner. Though the underlying Python\ncommands can be executed without it, we recommend [installing Task](https://taskfile.dev/installation/)\nfor ease of use. Details located in `Taskfile.yml`.\n\n#### Current commands\n\n```bash\n\u003e task -l\ntask: Available tasks for this project:\n* check-config:       Check Hydra configuration\n* compare:            Compare using linear baselines\n* train:              Train a model\n* wandb:              Login to Weights \u0026 Biases\n```\n\nExample: Train model and for `adult-income` dataset experiment\n\n*The `--` forwards CLI arguments to Hydra.*\n\n```bash\ntask train -- experiment=income\n```\n\n#### PDM\n\nThis project was built using [this cookiecutter](https://github.com/chris-santiago/cookie) and is\nsetup to use [PDM](https://pdm.fming.dev/latest/) for dependency management, though it's not required\nfor package installation.\n\n#### Weights and Biases\n\nThis project is set up to log experiment results with [Weights and Biases](https://wandb.ai/). It\nexpects an API key within a `.env` file in the root directory:\n\n```toml\nWANDB_KEY=\u003cmy-super-secret-key\u003e\n```\n\nUsers can configure different logger(s) within the `conf/trainer/default.yaml` file.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchris-santiago%2Fmet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchris-santiago%2Fmet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchris-santiago%2Fmet/lists"}