{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GY4TCXGMZU3TWMYMK5YV3VYLUW","short_pith_number":"pith:GY4TCXGM","schema_version":"1.0","canonical_sha256":"3639315ccccd373b330c57715dd70ba59085499f8d18863c35bcdf539f5144cc","source":{"kind":"arxiv","id":"2402.11139","version":1},"attestation_state":"computed","paper":{"title":"LiGNN: Graph Neural Networks at LinkedIn","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amol Ghoting, Baolei Li, Birjodh Tiwana, Chengming Jiang, Daqi Sun, David Stein, Fedor Borisyuk, Haichao Wei, Kuang-Hsuan Lee, Morteza Ramezani, Nitin Pasumarthy, Peng Du, Ping Liu, Priya Bannur, Qianqi Shen, Shihai He, Siddharth Dangi, Sirou Zhu, Souvik Ghosh, Xiaochen Hou, Xiao Shi, Yunbo Ouyang, Zhoutao Pei","submitted_at":"2024-02-17T00:10:33Z","abstract_excerpt":"In this paper, we present LiGNN, a deployed large-scale Graph Neural Networks (GNNs) Framework. We share our insight on developing and deployment of GNNs at large scale at LinkedIn. We present a set of algorithmic improvements to the quality of GNN representation learning including temporal graph architectures with long term losses, effective cold start solutions via graph densification, ID embeddings and multi-hop neighbor sampling. We explain how we built and sped up by 7x our large-scale training on LinkedIn graphs with adaptive sampling of neighbors, grouping and slicing of training data b"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.11139","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-17T00:10:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"100067e9a5f366241f0cb5cc6e5d95e1542d7dcbcf4946387a6426fb7129dbc0","abstract_canon_sha256":"dbca03bf0d4e31c80fdbc560fb6a84feb7804dfeb246ceabedd0e2c3214e2764"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:34.622254Z","signature_b64":"EXzyWgx58v1/B4aKSvIK84/ghdSuvZPMQnN0cE1sVqg0UyjUnsXxYOa2VXf3STiAmvYqm6UqKRL8kp1YeFlOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3639315ccccd373b330c57715dd70ba59085499f8d18863c35bcdf539f5144cc","last_reissued_at":"2026-07-05T07:46:34.621659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:34.621659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiGNN: Graph Neural Networks at LinkedIn","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amol Ghoting, Baolei Li, Birjodh Tiwana, Chengming Jiang, Daqi Sun, David Stein, Fedor Borisyuk, Haichao Wei, Kuang-Hsuan Lee, Morteza Ramezani, Nitin Pasumarthy, Peng Du, Ping Liu, Priya Bannur, Qianqi Shen, Shihai He, Siddharth Dangi, Sirou Zhu, Souvik Ghosh, Xiaochen Hou, Xiao Shi, Yunbo Ouyang, Zhoutao Pei","submitted_at":"2024-02-17T00:10:33Z","abstract_excerpt":"In this paper, we present LiGNN, a deployed large-scale Graph Neural Networks (GNNs) Framework. We share our insight on developing and deployment of GNNs at large scale at LinkedIn. We present a set of algorithmic improvements to the quality of GNN representation learning including temporal graph architectures with long term losses, effective cold start solutions via graph densification, ID embeddings and multi-hop neighbor sampling. We explain how we built and sped up by 7x our large-scale training on LinkedIn graphs with adaptive sampling of neighbors, grouping and slicing of training data b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11139","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.11139/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.11139","created_at":"2026-07-05T07:46:34.621731+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11139v1","created_at":"2026-07-05T07:46:34.621731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11139","created_at":"2026-07-05T07:46:34.621731+00:00"},{"alias_kind":"pith_short_12","alias_value":"GY4TCXGMZU3T","created_at":"2026-07-05T07:46:34.621731+00:00"},{"alias_kind":"pith_short_16","alias_value":"GY4TCXGMZU3TWMYM","created_at":"2026-07-05T07:46:34.621731+00:00"},{"alias_kind":"pith_short_8","alias_value":"GY4TCXGM","created_at":"2026-07-05T07:46:34.621731+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GY4TCXGMZU3TWMYMK5YV3VYLUW","json":"https://pith.science/pith/GY4TCXGMZU3TWMYMK5YV3VYLUW.json","graph_json":"https://pith.science/api/pith-number/GY4TCXGMZU3TWMYMK5YV3VYLUW/graph.json","events_json":"https://pith.science/api/pith-number/GY4TCXGMZU3TWMYMK5YV3VYLUW/events.json","paper":"https://pith.science/paper/GY4TCXGM"},"agent_actions":{"view_html":"https://pith.science/pith/GY4TCXGMZU3TWMYMK5YV3VYLUW","download_json":"https://pith.science/pith/GY4TCXGMZU3TWMYMK5YV3VYLUW.json","view_paper":"https://pith.science/paper/GY4TCXGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11139&json=true","fetch_graph":"https://pith.science/api/pith-number/GY4TCXGMZU3TWMYMK5YV3VYLUW/graph.json","fetch_events":"https://pith.science/api/pith-number/GY4TCXGMZU3TWMYMK5YV3VYLUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GY4TCXGMZU3TWMYMK5YV3VYLUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GY4TCXGMZU3TWMYMK5YV3VYLUW/action/storage_attestation","attest_author":"https://pith.science/pith/GY4TCXGMZU3TWMYMK5YV3VYLUW/action/author_attestation","sign_citation":"https://pith.science/pith/GY4TCXGMZU3TWMYMK5YV3VYLUW/action/citation_signature","submit_replication":"https://pith.science/pith/GY4TCXGMZU3TWMYMK5YV3VYLUW/action/replication_record"}},"created_at":"2026-07-05T07:46:34.621731+00:00","updated_at":"2026-07-05T07:46:34.621731+00:00"}