{"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/iglu-efficient-gcn-training-via-lazy-updates","title":"IGLU: Efficient GCN Training via Lazy Updates","arxiv_id":"2109.13995","date":"2021-09-28","proceeding":"ICLR 2022 4","authors":["S Deepak Narayanan","Aditya Sinha","Prateek Jain","Purushottam Kar","Sundararajan Sellamanickam"],"abstract":"Training multi-layer Graph Convolution Networks (GCN) using standard SGD techniques scales poorly as each descent step ends up updating node embeddings for a large portion of the graph. Recent attempts to remedy this sub-sample the graph that reduces compute but introduce additional variance and may offer suboptimal performance. This paper develops the IGLU method that caches intermediate computations at various GCN layers thus enabling lazy updates that significantly reduce the compute cost of descent. IGLU introduces bounded bias into the gradients but nevertheless converges to a first-order saddle point under standard assumptions such as objective smoothness. Benchmark experiments show that IGLU offers up to 1.2% better accuracy despite requiring up to 88% less compute.","url_abs":"https://arxiv.org/abs/2109.13995v2","url_pdf":"https://arxiv.org/pdf/2109.13995v2.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":"iglu-efficient-gcn-training-via-lazy-updates","repo_url":"https://github.com/sdeepaknarayanan/iglu","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.13995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.13995"}},"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":"deterministic:regex_extraction","url":"https://github.com/sdeepaknarayanan/iglu","reach":null}],"summary":{"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"a060f56f96557546","entry":"get_sparse_adj","repo":"sdeepaknarayanan/iglu","repo_kind":"official","path":"src/inductive/train_arxiv.py","file_url":"https://github.com/sdeepaknarayanan/iglu/blob/HEAD/src/inductive/train_arxiv.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a060f56f96557546"}},{"code_sha256_prefix":"9fb8a0022d6830ae","entry":"mini_batch_exact","repo":"sdeepaknarayanan/iglu","repo_kind":"official","path":"src/inductive/train_ppi.py","file_url":"https://github.com/sdeepaknarayanan/iglu/blob/HEAD/src/inductive/train_ppi.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9fb8a0022d6830ae"}},{"code_sha256_prefix":"fd53a8fff8553090","entry":"normalize","repo":"sdeepaknarayanan/iglu","repo_kind":"official","path":"src/inductive/train_arxiv.py","file_url":"https://github.com/sdeepaknarayanan/iglu/blob/HEAD/src/inductive/train_arxiv.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd53a8fff8553090"}},{"code_sha256_prefix":"63bc427d8591c5ca","entry":"convert_sparse_matrix_to_sparse_tensor","repo":"sdeepaknarayanan/iglu","repo_kind":"official","path":"src/inductive/train_arxiv.py","file_url":"https://github.com/sdeepaknarayanan/iglu/blob/HEAD/src/inductive/train_arxiv.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"63bc427d8591c5ca"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}