{"id":22229740,"url":"https://github.com/graph-com/layerdag","last_synced_at":"2025-07-27T19:31:37.916Z","repository":{"id":246703256,"uuid":"811168622","full_name":"Graph-COM/LayerDAG","owner":"Graph-COM","description":"[ICLR 2025 Spotlight] LayerDAG: A Layerwise Autoregressive Diffusion Model of Directed Acyclic Graphs","archived":false,"fork":false,"pushed_at":"2025-01-26T05:45:06.000Z","size":1301,"stargazers_count":15,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-04T06:51:12.528Z","etag":null,"topics":["autoregressive-models","dataflows","ddpm","directed-acyclic-graph","generative-model","graph-generation","graph-neural-networks","intermediate-representation","pytorch","synthetic-data-generation"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Graph-COM.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-06-06T04:30:54.000Z","updated_at":"2025-03-31T14:08:15.000Z","dependencies_parsed_at":"2024-11-09T16:29:07.503Z","dependency_job_id":"4b115ace-c6b6-4df8-902a-99be3075bc33","html_url":"https://github.com/Graph-COM/LayerDAG","commit_stats":null,"previous_names":["graph-com/layerdag"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Graph-COM/LayerDAG","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Graph-COM%2FLayerDAG","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Graph-COM%2FLayerDAG/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Graph-COM%2FLayerDAG/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Graph-COM%2FLayerDAG/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Graph-COM","download_url":"https://codeload.github.com/Graph-COM/LayerDAG/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Graph-COM%2FLayerDAG/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267413654,"owners_count":24083470,"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":"2025-07-27T02:00:11.917Z","response_time":82,"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":["autoregressive-models","dataflows","ddpm","directed-acyclic-graph","generative-model","graph-generation","graph-neural-networks","intermediate-representation","pytorch","synthetic-data-generation"],"created_at":"2024-12-03T01:12:10.141Z","updated_at":"2025-07-27T19:31:37.904Z","avatar_url":"https://github.com/Graph-COM.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LayerDAG\n\n[[Paper]](https://arxiv.org/abs/2411.02322)\n\n## Table of Contents\n\n- [Installation](#installation)\n- [Train](#train)\n- [Sample](#sample)\n- [Eval](#eval)\n- [Frequently Asked Questions](#frequently-asked-questions)\n  * [Q1: libcusparse.so](#q1-libcusparseso)\n- [Citation](#citation)\n\n## Installation\n\n```bash\nconda create -n LayerDAG python=3.10 -y\nconda activate LayerDAG\npip install torch==1.12.0+cu116 --extra-index-url https://download.pytorch.org/whl/cu116\nconda install -c conda-forge cudatoolkit=11.6\nconda clean --all -y\npip install dgl==1.1.0+cu116 -f https://data.dgl.ai/wheels/cu116/repo.html\npip install tqdm einops wandb pydantic pandas\npip install numpy==1.26.3\n```\n\n## Train\n\nTo train a LayerDAG model,\n\n```bash\npython train.py --config_file configs/LayerDAG/tpu_tile.yaml\n```\n\nThe trained model checkpoint will be saved to a file `model_tpu_tile_{time_stamp}.pth`.\n\n## Sample\n\nFor sampling and evaluation,\n\n```bash\npython sample.py --model_path X\n```\n\nwhere `X` is the file `model_tpu_tile_{time_stamp}.pth` saved above.\n\n## Frequently Asked Questions\n\n### Q1: libcusparse.so\n\n**An error occurs that the program cannot find `libcusparse.so`**, e.g., OSError: libcusparse.so.11: cannot open shared object file: No such file or directory.\n\nTo search for the location of it on linux,\n\n```bash\nfind /path/to/directory -name libcusparse.so.11 -exec realpath {} \\;\n```\n\nwhere `/path/to/directory` is the directory you want to search. Assume that the search returns `/home/miniconda3/envs/LayerDAG/lib/libcusparse.so.11`. Then you need to manually specify the environment variable as follows.\n\n```bash\nexport LD_LIBRARY_PATH=/home/miniconda3/envs/LayerDAG/lib:$LD_LIBRARY_PATH\n```\n\n## Citation\n\n```\n@inproceedings{li2024layerdag,\n    title={Layer{DAG}: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation},\n    author={Mufei Li and Viraj Shitole and Eli Chien and Changhai Man and Zhaodong Wang and Srinivas Sridharan and Ying Zhang and Tushar Krishna and Pan Li},\n    booktitle={International Conference on Learning Representations},\n    year={2025}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgraph-com%2Flayerdag","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgraph-com%2Flayerdag","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgraph-com%2Flayerdag/lists"}