{"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/towards-sparsification-of-graph-neural","title":"Towards Sparsification of Graph Neural Networks","arxiv_id":"2209.04766","date":"2022-09-11","proceeding":null,"authors":["Hongwu Peng","Deniz Gurevin","Shaoyi Huang","Tong Geng","Weiwen Jiang","Omer Khan","Caiwen Ding"],"abstract":"As real-world graphs expand in size, larger GNN models with billions of parameters are deployed. High parameter count in such models makes training and inference on graphs expensive and challenging. To reduce the computational and memory costs of GNNs, optimization methods such as pruning the redundant nodes and edges in input graphs have been commonly adopted. However, model compression, which directly targets the sparsification of model layers, has been mostly limited to traditional Deep Neural Networks (DNNs) used for tasks such as image classification and object detection. In this paper, we utilize two state-of-the-art model compression methods (1) train and prune and (2) sparse training for the sparsification of weight layers in GNNs. We evaluate and compare the efficiency of both methods in terms of accuracy, training sparsity, and training FLOPs on real-world graphs. Our experimental results show that on the ia-email, wiki-talk, and stackoverflow datasets for link prediction, sparse training with much lower training FLOPs achieves a comparable accuracy with the train and prune method. On the brain dataset for node classification, sparse training uses a lower number FLOPs (less than 1/7 FLOPs of train and prune method) and preserves a much better accuracy performance under extreme model sparsity.","url_abs":"https://arxiv.org/abs/2209.04766v3","url_pdf":"https://arxiv.org/pdf/2209.04766v3.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":"towards-sparsification-of-graph-neural","repo_url":"https://github.com/harveyp123/iccd_sptrn_slr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"model-compression","task_name":"Model Compression"},{"task_slug":"node-classification","task_name":"Node Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2209.04766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.04766"}},"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/harveyp123/iccd_sptrn_slr","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"5810861539466cc4","entry":"L1_pruning","repo":"harveyp123/iccd_sptrn_slr","repo_kind":"official","path":"SLR_GCN_Node_Class/admm.py","file_url":"https://github.com/harveyp123/iccd_sptrn_slr/blob/HEAD/SLR_GCN_Node_Class/admm.py","link_basis":"harvester_set","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":"5810861539466cc4"}},{"code_sha256_prefix":"b7c8ba50fb920c3c","entry":"calculate_unused_weight","repo":"harveyp123/iccd_sptrn_slr","repo_kind":"official","path":"SLR_GCN_Node_Class/testers.py","file_url":"https://github.com/harveyp123/iccd_sptrn_slr/blob/HEAD/SLR_GCN_Node_Class/testers.py","link_basis":"harvester_set","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":"b7c8ba50fb920c3c"}},{"code_sha256_prefix":"285a08a5c6aa47e3","entry":"get_logger","repo":"harveyp123/iccd_sptrn_slr","repo_kind":"official","path":"SLR_GCN_Node_Class/utils.py","file_url":"https://github.com/harveyp123/iccd_sptrn_slr/blob/HEAD/SLR_GCN_Node_Class/utils.py","link_basis":"harvester_set","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":"285a08a5c6aa47e3"}},{"code_sha256_prefix":"b5c1496bb0f182ff","entry":"parse_gpus","repo":"harveyp123/iccd_sptrn_slr","repo_kind":"official","path":"SLR_GCN_Node_Class/utils.py","file_url":"https://github.com/harveyp123/iccd_sptrn_slr/blob/HEAD/SLR_GCN_Node_Class/utils.py","link_basis":"harvester_set","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":"b5c1496bb0f182ff"}},{"code_sha256_prefix":"1e0ce7837750e479","entry":"random_pruning","repo":"harveyp123/iccd_sptrn_slr","repo_kind":"official","path":"SLR_GCN_Node_Class/admm.py","file_url":"https://github.com/harveyp123/iccd_sptrn_slr/blob/HEAD/SLR_GCN_Node_Class/admm.py","link_basis":"harvester_set","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":"1e0ce7837750e479"}},{"code_sha256_prefix":"abc5fc870ed054b3","entry":"total_params","repo":"harveyp123/iccd_sptrn_slr","repo_kind":"official","path":"SLR_Link_Pred/main_admm.py","file_url":"https://github.com/harveyp123/iccd_sptrn_slr/blob/HEAD/SLR_Link_Pred/main_admm.py","link_basis":"harvester_set","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":"abc5fc870ed054b3"}},{"code_sha256_prefix":"16d4dee8338d18dc","entry":"weight_pruning","repo":"harveyp123/iccd_sptrn_slr","repo_kind":"official","path":"SLR_GCN_Node_Class/admm.py","file_url":"https://github.com/harveyp123/iccd_sptrn_slr/blob/HEAD/SLR_GCN_Node_Class/admm.py","link_basis":"harvester_set","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":"16d4dee8338d18dc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}