{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/network-in-graph-neural-network","title":"Network In Graph Neural Network","arxiv_id":"2111.11638","date":"2021-11-23","proceeding":null,"authors":["Xiang Song","Runjie Ma","Jiahang Li","Muhan Zhang","David Paul Wipf"],"abstract":"Graph Neural Networks (GNNs) have shown success in learning from graph structured data containing node/edge feature information, with application to social networks, recommendation, fraud detection and knowledge graph reasoning. In this regard, various strategies have been proposed in the past to improve the expressiveness of GNNs. For example, one straightforward option is to simply increase the parameter size by either expanding the hid-den dimension or increasing the number of GNN layers. However, wider hidden layers can easily lead to overfitting, and incrementally adding more GNN layers can potentially result in over-smoothing.In this paper, we present a model-agnostic methodology, namely Network In Graph Neural Network (NGNN ), that allows arbitrary GNN models to increase their model capacity by making the model deeper. However, instead of adding or widening GNN layers, NGNN deepens a GNN model by inserting non-linear feedforward neural network layer(s) within each GNN layer. An analysis of NGNN as applied to a GraphSage base GNN on ogbn-products data demonstrate that it can keep the model stable against either node feature or graph structure perturbations. Furthermore, wide-ranging evaluation results on both node classification and link prediction tasks show that NGNN works reliably across diverse GNN architectures.For instance, it improves the test accuracy of GraphSage on the ogbn-products by 1.6% and improves the hits@100 score of SEAL on ogbl-ppa by 7.08% and the hits@20 score of GraphSage+Edge-Attr on ogbl-ppi by 6.22%. And at the time of this submission, it achieved two first places on the OGB link prediction leaderboard.","url_abs":"https://arxiv.org/abs/2111.11638v1","url_pdf":"https://arxiv.org/pdf/2111.11638v1.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":[],"tasks":[{"task_slug":"fraud-detection","task_name":"Fraud Detection"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"},{"method_slug":"graphsage","method_name":"GraphSAGE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-property-prediction-on-ogbl-citation2","task":"Link Property Prediction","dataset":"ogbl-citation2","model":"NGNN + SEAL","rank_in_archive_order":7,"of":23,"metrics":{"Ext. data":"No","Number of params":"1134402","Test MRR":"0.8891 ± 0.0022","Validation MRR":"0.8879 ± 0.0022"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-collab","task":"Link Property Prediction","dataset":"ogbl-collab","model":"NGNN + GraphSAGE","rank_in_archive_order":20,"of":34,"metrics":{"Ext. data":"No","Number of params":"591873","Test Hits@50":"0.5359 ± 0.0056","Validation Hits@50":"0.6281 ± 0.0046"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-collab","task":"Link Property Prediction","dataset":"ogbl-collab","model":"NGNN + GCN","rank_in_archive_order":21,"of":34,"metrics":{"Ext. data":"No","Number of params":"428033","Test Hits@50":"0.5348 ± 0.0040","Validation Hits@50":"0.6273 ± 0.0040"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-ddi","task":"Link Property Prediction","dataset":"ogbl-ddi","model":"NGNN + GraphSAGE","rank_in_archive_order":22,"of":31,"metrics":{"Ext. data":"No","Number of params":"1618433","Test Hits@20":"0.5770 ± 0.1523","Validation Hits@20":"0.7323 ± 0.0040"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-ddi","task":"Link Property Prediction","dataset":"ogbl-ddi","model":"NGNN + GCN","rank_in_archive_order":23,"of":31,"metrics":{"Ext. data":"No","Number of params":"1487361","Test Hits@20":"0.5483 ± 0.1581","Validation Hits@20":"0.7121 ± 0.0038"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-ppa","task":"Link Property Prediction","dataset":"ogbl-ppa","model":"NGNN + SEAL","rank_in_archive_order":8,"of":26,"metrics":{"Ext. data":"No","Number of params":"735426","Test Hits@100":"0.5971 ± 0.0245","Validation Hits@100":"0.5995 ± 0.0205"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-ppa","task":"Link Property Prediction","dataset":"ogbl-ppa","model":"NGNN + GraphSAGE","rank_in_archive_order":18,"of":26,"metrics":{"Ext. data":"No","Number of params":"556033","Test Hits@100":"0.4005 ± 0.0138","Validation Hits@100":"0.4058 ± 0.0123"},"uses_additional_data":false},{"leaderboard":"/sota/link-property-prediction-on-ogbl-ppa","task":"Link Property Prediction","dataset":"ogbl-ppa","model":"NGNN + GCN","rank_in_archive_order":19,"of":26,"metrics":{"Ext. data":"No","Number of params":"410113","Test Hits@100":"0.3683 ± 0.0099","Validation Hits@100":"0.3834 ± 0.0082"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-proteins","task":"Node Property Prediction","dataset":"ogbn-proteins","model":"GAT+BOT+NGNN","rank_in_archive_order":5,"of":26,"metrics":{"Ext. data":"No","Number of params":"11740552","Test ROC-AUC":"0.8809 ± 0.0016","Validation ROC-AUC":"0.9375 ± 0.0019"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.11638","atlas_url":"https://app.syntology.ai/?focus=2111.11638","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2111.11638"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2111.11638\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2111.11638"},"call":"get_concepts_for_paper(arxiv_id=\"2111.11638\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0af67fa146f8f989b5af9e06e2baafd45f116a71936e3d609c67bc3020e9de98","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}