{"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/dgl-ke-training-knowledge-graph-embeddings-at","title":"DGL-KE: Training Knowledge Graph Embeddings at Scale","arxiv_id":"2004.08532","date":"2020-04-18","proceeding":null,"authors":["Da Zheng","Xiang Song","Chao Ma","Zeyuan Tan","Zihao Ye","Jin Dong","Hao Xiong","Zheng Zhang","George Karypis"],"abstract":"Knowledge graphs have emerged as a key abstraction for organizing information in diverse domains and their embeddings are increasingly used to harness their information in various information retrieval and machine learning tasks. However, the ever growing size of knowledge graphs requires computationally efficient algorithms capable of scaling to graphs with millions of nodes and billions of edges. This paper presents DGL-KE, an open-source package to efficiently compute knowledge graph embeddings. DGL-KE introduces various novel optimizations that accelerate training on knowledge graphs with millions of nodes and billions of edges using multi-processing, multi-GPU, and distributed parallelism. These optimizations are designed to increase data locality, reduce communication overhead, overlap computations with memory accesses, and achieve high operation efficiency. Experiments on knowledge graphs consisting of over 86M nodes and 338M edges show that DGL-KE can compute embeddings in 100 minutes on an EC2 instance with 8 GPUs and 30 minutes on an EC2 cluster with 4 machines with 48 cores/machine. These results represent a 2x~5x speedup over the best competing approaches. DGL-KE is available on https://github.com/awslabs/dgl-ke.","url_abs":"https://arxiv.org/abs/2004.08532v1","url_pdf":"https://arxiv.org/pdf/2004.08532v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"dgl-ke-training-knowledge-graph-embeddings-at","repo_url":"https://github.com/awslabs/dgl-ke","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"dgl-ke-training-knowledge-graph-embeddings-at","repo_url":"https://github.com/idirlab/freebases","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"CC0-1.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.08532","atlas_url":"https://app.syntology.ai/?focus=2004.08532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08532"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/idirlab/freebases","reach":{"status":"ok","spdx":"CC0-1.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/awslabs/dgl-ke","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":15,"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":4,"repositories":1},"listed":{"samples":15,"ran":11,"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":"dd8acaaab9a42aa5","entry":"cartesian_relations","repo":"idirlab/freebases","repo_kind":"listed","path":"DataPreparationScripts/cartesian.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/DataPreparationScripts/cartesian.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dd8acaaab9a42aa5"}},{"code_sha256_prefix":"bc3a10c2f9154e25","entry":"check_port_available","repo":"awslabs/dgl-ke","repo_kind":"official","path":"python/dglke/kvserver.py","file_url":"https://github.com/awslabs/dgl-ke/blob/HEAD/python/dglke/kvserver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bc3a10c2f9154e25"}},{"code_sha256_prefix":"0c1f71b8bac6e691","entry":"create_triples","repo":"idirlab/freebases","repo_kind":"listed","path":"DataPreparationScripts/cartesian.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/DataPreparationScripts/cartesian.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0c1f71b8bac6e691"}},{"code_sha256_prefix":"391f5f5a397f785d","entry":"create_triples","repo":"idirlab/freebases","repo_kind":"listed","path":"DataPreparationScripts/duplicate.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/DataPreparationScripts/duplicate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"391f5f5a397f785d"}},{"code_sha256_prefix":"cbf9223db5e0b8ba","entry":"duplicate_relations","repo":"idirlab/freebases","repo_kind":"listed","path":"DataPreparationScripts/duplicate.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/DataPreparationScripts/duplicate.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cbf9223db5e0b8ba"}},{"code_sha256_prefix":"e9baa88374fa3160","entry":"entity_dict","repo":"idirlab/freebases","repo_kind":"listed","path":"ExperimentsScripts/data_preparation/create_er_dicts.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/ExperimentsScripts/data_preparation/create_er_dicts.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e9baa88374fa3160"}},{"code_sha256_prefix":"36dfb609acf78036","entry":"find_edge_domain","repo":"idirlab/freebases","repo_kind":"listed","path":"ExperimentsScripts/FB1_statistics_domain_triples_relations.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/ExperimentsScripts/FB1_statistics_domain_triples_relations.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"36dfb609acf78036"}},{"code_sha256_prefix":"5b9798142c710f46","entry":"get_id2label","repo":"idirlab/freebases","repo_kind":"listed","path":"ExperimentsScripts/FB1_statistics_domain_triples_relations.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/ExperimentsScripts/FB1_statistics_domain_triples_relations.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5b9798142c710f46"}},{"code_sha256_prefix":"2d755fd7759a79cc","entry":"get_machine_count","repo":"awslabs/dgl-ke","repo_kind":"official","path":"python/dglke/dist_train.py","file_url":"https://github.com/awslabs/dgl-ke/blob/HEAD/python/dglke/dist_train.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2d755fd7759a79cc"}},{"code_sha256_prefix":"14d9fe99228da0c1","entry":"get_machine_count","repo":"awslabs/dgl-ke","repo_kind":"official","path":"python/dglke/kvclient.py","file_url":"https://github.com/awslabs/dgl-ke/blob/HEAD/python/dglke/kvclient.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"14d9fe99228da0c1"}},{"code_sha256_prefix":"df9fc541b4d9d076","entry":"read_dict","repo":"idirlab/freebases","repo_kind":"listed","path":"ExperimentsScripts/data_preparation/map_triples_to_ids.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/ExperimentsScripts/data_preparation/map_triples_to_ids.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"df9fc541b4d9d076"}},{"code_sha256_prefix":"da36ef8474d88ac2","entry":"read_file","repo":"idirlab/freebases","repo_kind":"listed","path":"ExperimentsScripts/FB1_statistics_domain_triples_relations.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/ExperimentsScripts/FB1_statistics_domain_triples_relations.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"da36ef8474d88ac2"}},{"code_sha256_prefix":"e71bc2d8ce60d3ff","entry":"relation_dict","repo":"idirlab/freebases","repo_kind":"listed","path":"ExperimentsScripts/data_preparation/create_er_dicts.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/ExperimentsScripts/data_preparation/create_er_dicts.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e71bc2d8ce60d3ff"}},{"code_sha256_prefix":"a058bd02af0f0c57","entry":"replaceWID","repo":"idirlab/freebases","repo_kind":"listed","path":"ExperimentsScripts/data_preparation/map_triples_to_ids.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/ExperimentsScripts/data_preparation/map_triples_to_ids.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a058bd02af0f0c57"}},{"code_sha256_prefix":"13997ea0dc0416ad","entry":"run_cmd","repo":"awslabs/dgl-ke","repo_kind":"official","path":"python/dglke/dist_train.py","file_url":"https://github.com/awslabs/dgl-ke/blob/HEAD/python/dglke/dist_train.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"13997ea0dc0416ad"}},{"code_sha256_prefix":"51ced90c9fe3686a","entry":"get_local_machine_id","repo":"awslabs/dgl-ke","repo_kind":"official","path":"python/dglke/kvclient.py","file_url":"https://github.com/awslabs/dgl-ke/blob/HEAD/python/dglke/kvclient.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":"51ced90c9fe3686a"}},{"code_sha256_prefix":"210da1d26a3627d6","entry":"get_long_tail_partition","repo":"awslabs/dgl-ke","repo_kind":"official","path":"python/dglke/kvclient.py","file_url":"https://github.com/awslabs/dgl-ke/blob/HEAD/python/dglke/kvclient.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":"210da1d26a3627d6"}},{"code_sha256_prefix":"249d1c8c4c51f698","entry":"get_server_data","repo":"awslabs/dgl-ke","repo_kind":"official","path":"python/dglke/kvserver.py","file_url":"https://github.com/awslabs/dgl-ke/blob/HEAD/python/dglke/kvserver.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":"249d1c8c4c51f698"}},{"code_sha256_prefix":"79e8c86b8cbf34bf","entry":"index_KvsAll","repo":"idirlab/freebases","repo_kind":"listed","path":"ExperimentsScripts/kge/kge/indexing.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/ExperimentsScripts/kge/kge/indexing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"79e8c86b8cbf34bf"}},{"code_sha256_prefix":"8de5ea6adbb76af2","entry":"index_relation_types","repo":"idirlab/freebases","repo_kind":"listed","path":"ExperimentsScripts/kge/kge/indexing.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/ExperimentsScripts/kge/kge/indexing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8de5ea6adbb76af2"}},{"code_sha256_prefix":"016f6033e3fdf5c1","entry":"index_relations_per_type","repo":"idirlab/freebases","repo_kind":"listed","path":"ExperimentsScripts/kge/kge/indexing.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/ExperimentsScripts/kge/kge/indexing.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"016f6033e3fdf5c1"}},{"code_sha256_prefix":"1bed5159d4510f5a","entry":"is_local","repo":"awslabs/dgl-ke","repo_kind":"official","path":"python/dglke/dist_train.py","file_url":"https://github.com/awslabs/dgl-ke/blob/HEAD/python/dglke/dist_train.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":"1bed5159d4510f5a"}},{"code_sha256_prefix":"099352c8df6bbfe5","entry":"load_model","repo":"awslabs/dgl-ke","repo_kind":"official","path":"python/dglke/train_mxnet.py","file_url":"https://github.com/awslabs/dgl-ke/blob/HEAD/python/dglke/train_mxnet.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":"099352c8df6bbfe5"}},{"code_sha256_prefix":"4bc4112f66051106","entry":"load_model_from_checkpoint","repo":"awslabs/dgl-ke","repo_kind":"official","path":"python/dglke/train_mxnet.py","file_url":"https://github.com/awslabs/dgl-ke/blob/HEAD/python/dglke/train_mxnet.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":"4bc4112f66051106"}},{"code_sha256_prefix":"a943b8e45daa74e9","entry":"splitData","repo":"idirlab/freebases","repo_kind":"listed","path":"ExperimentsScripts/data_preparation/split_no_cvt_data.py","file_url":"https://github.com/idirlab/freebases/blob/HEAD/ExperimentsScripts/data_preparation/split_no_cvt_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a943b8e45daa74e9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}