{"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/efficient-heterogeneous-graph-learning-via","title":"Efficient Heterogeneous Graph Learning via Random Projection","arxiv_id":"2310.14481","date":"2023-10-23","proceeding":null,"authors":["Jun Hu","Bryan Hooi","Bingsheng He"],"abstract":"Heterogeneous Graph Neural Networks (HGNNs) are powerful tools for deep learning on heterogeneous graphs. Typical HGNNs require repetitive message passing during training, limiting efficiency for large-scale real-world graphs. Recent pre-computation-based HGNNs use one-time message passing to transform a heterogeneous graph into regular-shaped tensors, enabling efficient mini-batch training. Existing pre-computation-based HGNNs can be mainly categorized into two styles, which differ in how much information loss is allowed and efficiency. We propose a hybrid pre-computation-based HGNN, named Random Projection Heterogeneous Graph Neural Network (RpHGNN), which combines the benefits of one style's efficiency with the low information loss of the other style. To achieve efficiency, the main framework of RpHGNN consists of propagate-then-update iterations, where we introduce a Random Projection Squashing step to ensure that complexity increases only linearly. To achieve low information loss, we introduce a Relation-wise Neighbor Collection component with an Even-odd Propagation Scheme, which aims to collect information from neighbors in a finer-grained way. Experimental results indicate that our approach achieves state-of-the-art results on seven small and large benchmark datasets while also being 230% faster compared to the most effective baseline. Surprisingly, our approach not only surpasses pre-processing-based baselines but also outperforms end-to-end methods.","url_abs":"https://arxiv.org/abs/2310.14481v2","url_pdf":"https://arxiv.org/pdf/2310.14481v2.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":"efficient-heterogeneous-graph-learning-via","repo_url":"https://github.com/CrawlScript/RpHGNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"heterogeneous-node-classification","task_name":"Heterogeneous Node Classification"},{"task_slug":"node-property-prediction","task_name":"Node Property Prediction"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/heterogeneous-node-classification-on-acm","task":"Heterogeneous Node Classification","dataset":"ACM (Heterogeneous Node Classification)","model":"RpHGNN","rank_in_archive_order":1,"of":11,"metrics":{" Macro-F1":"94.09","Micro-F1":"94.04"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-dblp-2","task":"Heterogeneous Node Classification","dataset":"DBLP (Heterogeneous Node Classification)","model":"RpHGNN","rank_in_archive_order":1,"of":11,"metrics":{" Macro-F1":"95.23","Micro-F1":"95.55"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-freebase","task":"Heterogeneous Node Classification","dataset":"Freebase (Heterogeneous Node Classification)","model":"RpHGNN","rank_in_archive_order":1,"of":9,"metrics":{" Macro-F1":"54.02","Micro-F1":"66.55"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-imdb","task":"Heterogeneous Node Classification","dataset":"IMDB (Heterogeneous Node Classification)","model":"RpHGNN","rank_in_archive_order":1,"of":11,"metrics":{" Macro-F1":"67.53","Micro-F1":"69.77"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-oag-l1","task":"Heterogeneous Node Classification","dataset":"OAG-L1-Field","model":"RpHGNN","rank_in_archive_order":1,"of":5,"metrics":{"MRR":"86.79","NDCG":"87.80"},"uses_additional_data":false},{"leaderboard":"/sota/heterogeneous-node-classification-on-oag","task":"Heterogeneous Node Classification","dataset":"OAG-Venue","model":"RpHGNN","rank_in_archive_order":1,"of":5,"metrics":{"MRR":"35.46","NDCG":"53.31"},"uses_additional_data":false},{"leaderboard":"/sota/node-property-prediction-on-ogbn-mag","task":"Node Property Prediction","dataset":"ogbn-mag","model":"RpHGNN+LP+CR (LINE embs)","rank_in_archive_order":5,"of":39,"metrics":{"Ext. data":"No","Number of params":"7720368","Test Accuracy":"0.5773 ± 0.0012","Validation Accuracy":"0.5973 ± 0.0008"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.14481","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.14481"}},"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/CrawlScript/RpHGNN","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran":5,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"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":8,"samples":[{"code_sha256_prefix":"cc601566939bf390","entry":"create_act","repo":"CrawlScript/RpHGNN","repo_kind":"official","path":"rphgnn/layers/rphgnn_encoder.py","file_url":"https://github.com/CrawlScript/RpHGNN/blob/HEAD/rphgnn/layers/rphgnn_encoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"cc601566939bf390"}},{"code_sha256_prefix":"e3c137a431a3a8d8","entry":"kl_loss","repo":"CrawlScript/RpHGNN","repo_kind":"official","path":"rphgnn/losses.py","file_url":"https://github.com/CrawlScript/RpHGNN/blob/HEAD/rphgnn/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"e3c137a431a3a8d8"}},{"code_sha256_prefix":"32cb50833ad73ecb","entry":"load_default_param_config","repo":"CrawlScript/RpHGNN","repo_kind":"official","path":"rphgnn/configs/default_param_config.py","file_url":"https://github.com/CrawlScript/RpHGNN/blob/HEAD/rphgnn/configs/default_param_config.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"32cb50833ad73ecb"}},{"code_sha256_prefix":"27df8c68cb97d51c","entry":"mean_reciprocal_rank","repo":"CrawlScript/RpHGNN","repo_kind":"official","path":"rphgnn/utils/metrics_utils.py","file_url":"https://github.com/CrawlScript/RpHGNN/blob/HEAD/rphgnn/utils/metrics_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"27df8c68cb97d51c"}},{"code_sha256_prefix":"1f699858e6aedac4","entry":"torch_svd","repo":"CrawlScript/RpHGNN","repo_kind":"official","path":"rphgnn/layers/rphgnn_pre.py","file_url":"https://github.com/CrawlScript/RpHGNN/blob/HEAD/rphgnn/layers/rphgnn_pre.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1f699858e6aedac4"}},{"code_sha256_prefix":"98dab8054ae3ccee","entry":"dcg_at_k","repo":"CrawlScript/RpHGNN","repo_kind":"official","path":"rphgnn/utils/metrics_utils.py","file_url":"https://github.com/CrawlScript/RpHGNN/blob/HEAD/rphgnn/utils/metrics_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"98dab8054ae3ccee"}},{"code_sha256_prefix":"8ed96c2e50327534","entry":"get_raw_etype","repo":"CrawlScript/RpHGNN","repo_kind":"official","path":"rphgnn/layers/rphgnn_pre.py","file_url":"https://github.com/CrawlScript/RpHGNN/blob/HEAD/rphgnn/layers/rphgnn_pre.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"8ed96c2e50327534"}},{"code_sha256_prefix":"46e47a2c4cf98c1f","entry":"ndcg_at_k","repo":"CrawlScript/RpHGNN","repo_kind":"official","path":"rphgnn/utils/metrics_utils.py","file_url":"https://github.com/CrawlScript/RpHGNN/blob/HEAD/rphgnn/utils/metrics_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"46e47a2c4cf98c1f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}