{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dag-gnn-dag-structure-learning-with-graph","title":"DAG-GNN: DAG Structure Learning with Graph Neural Networks","arxiv_id":"1904.10098","date":"2019-04-22","proceeding":null,"authors":["Yue Yu","Jie Chen","Tian Gao","Mo Yu"],"abstract":"Learning a faithful directed acyclic graph (DAG) from samples of a joint\ndistribution is a challenging combinatorial problem, owing to the intractable\nsearch space superexponential in the number of graph nodes. A recent\nbreakthrough formulates the problem as a continuous optimization with a\nstructural constraint that ensures acyclicity (Zheng et al., 2018). The authors\napply the approach to the linear structural equation model (SEM) and the\nleast-squares loss function that are statistically well justified but\nnevertheless limited. Motivated by the widespread success of deep learning that\nis capable of capturing complex nonlinear mappings, in this work we propose a\ndeep generative model and apply a variant of the structural constraint to learn\nthe DAG. At the heart of the generative model is a variational autoencoder\nparameterized by a novel graph neural network architecture, which we coin\nDAG-GNN. In addition to the richer capacity, an advantage of the proposed model\nis that it naturally handles discrete variables as well as vector-valued ones.\nWe demonstrate that on synthetic data sets, the proposed method learns more\naccurate graphs for nonlinearly generated samples; and on benchmark data sets\nwith discrete variables, the learned graphs are reasonably close to the global\noptima. The code is available at \\url{https://github.com/fishmoon1234/DAG-GNN}.","url_abs":"http://arxiv.org/abs/1904.10098v1","url_pdf":"http://arxiv.org/pdf/1904.10098v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dag-gnn-dag-structure-learning-with-graph","repo_url":"https://github.com/fishmoon1234/DAG-GNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"dag-gnn-dag-structure-learning-with-graph","repo_url":"https://github.com/ElliottKasoar/GeneVAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"dag-gnn-dag-structure-learning-with-graph","repo_url":"https://github.com/ElliottKasoar/gene-dag-vae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.10098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.10098"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fishmoon1234/DAG-GNN","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ElliottKasoar/gene-dag-vae","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ElliottKasoar/GeneVAE","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"baa9dffef57d0cca","entry":"simulate_population_sample","repo":"fishmoon1234/DAG-GNN","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/fishmoon1234/DAG-GNN/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"baa9dffef57d0cca"}},{"code_sha256_prefix":"240110a44f90ebf7","entry":"simulate_random_dag","repo":"fishmoon1234/DAG-GNN","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/fishmoon1234/DAG-GNN/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"240110a44f90ebf7"}},{"code_sha256_prefix":"0aa08b9c5d0eef37","entry":"simulate_sem","repo":"fishmoon1234/DAG-GNN","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/fishmoon1234/DAG-GNN/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0aa08b9c5d0eef37"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}