{"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/gipa-general-information-propagation","title":"GIPA: General Information Propagation Algorithm for Graph Learning","arxiv_id":"2105.06035","date":"2021-05-13","proceeding":null,"authors":["Qinkai Zheng","Houyi Li","Peng Zhang","Zhixiong Yang","Guowei Zhang","Xintan Zeng","Yongchao Liu"],"abstract":"Graph neural networks (GNNs) have been popularly used in analyzing graph-structured data, showing promising results in various applications such as node classification, link prediction and network recommendation. In this paper, we present a new graph attention neural network, namely GIPA, for attributed graph data learning. GIPA consists of three key components: attention, feature propagation and aggregation. Specifically, the attention component introduces a new multi-layer perceptron based multi-head to generate better non-linear feature mapping and representation than conventional implementations such as dot-product. The propagation component considers not only node features but also edge features, which differs from existing GNNs that merely consider node features. The aggregation component uses a residual connection to generate the final embedding. We evaluate the performance of GIPA using the Open Graph Benchmark proteins (ogbn-proteins for short) dataset. The experimental results reveal that GIPA can beat the state-of-the-art models in terms of prediction accuracy, e.g., GIPA achieves an average test ROC-AUC of $0.8700\\pm 0.0010$ and outperforms all the previous methods listed in the ogbn-proteins leaderboard.","url_abs":"https://arxiv.org/abs/2105.06035v2","url_pdf":"https://arxiv.org/pdf/2105.06035v2.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":"gipa-general-information-propagation","repo_url":"https://github.com/yongchao-liu/gipa","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"gipa-general-information-propagation","repo_url":"https://github.com/houyili/gipa_wide_deep","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-attention","task_name":"Graph Attention"},{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/node-property-prediction-on-ogbn-proteins","task":"Node Property Prediction","dataset":"ogbn-proteins","model":"GIPA","rank_in_archive_order":9,"of":26,"metrics":{"Ext. data":"No","Number of params":"4831056","Test ROC-AUC":"0.8700 ± 0.0010","Validation ROC-AUC":"0.9187 ± 0.0003"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}