{"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/contextgnn-beyond-two-tower-recommendation","title":"ContextGNN: Beyond Two-Tower Recommendation Systems","arxiv_id":"2411.19513","date":"2024-11-29","proceeding":null,"authors":["Yiwen Yuan","Zecheng Zhang","Xinwei He","Akihiro Nitta","Weihua Hu","Dong Wang","Manan Shah","Shenyang Huang","Blaž Stojanovič","Alan Krumholz","Jan Eric Lenssen","Jure Leskovec","Matthias Fey"],"abstract":"Recommendation systems predominantly utilize two-tower architectures, which evaluate user-item rankings through the inner product of their respective embeddings. However, one key limitation of two-tower models is that they learn a pair-agnostic representation of users and items. In contrast, pair-wise representations either scale poorly due to their quadratic complexity or are too restrictive on the candidate pairs to rank. To address these issues, we introduce Context-based Graph Neural Networks (ContextGNNs), a novel deep learning architecture for link prediction in recommendation systems. The method employs a pair-wise representation technique for familiar items situated within a user's local subgraph, while leveraging two-tower representations to facilitate the recommendation of exploratory items. A final network then predicts how to fuse both pair-wise and two-tower recommendations into a single ranking of items. We demonstrate that ContextGNN is able to adapt to different data characteristics and outperforms existing methods, both traditional and GNN-based, on a diverse set of practical recommendation tasks, improving performance by 20% on average.","url_abs":"https://arxiv.org/abs/2411.19513v1","url_pdf":"https://arxiv.org/pdf/2411.19513v1.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":"contextgnn-beyond-two-tower-recommendation","repo_url":"https://github.com/kumo-ai/ContextGNN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.19513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.19513"}},"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/kumo-ai/ContextGNN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"a5f2d5dedfa2d00f","entry":"calculate_hit_rate_ndcg","repo":"kumo-ai/ContextGNN","repo_kind":"official","path":"contextgnn/utils/metrics.py","file_url":"https://github.com/kumo-ai/ContextGNN/blob/HEAD/contextgnn/utils/metrics.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":"a5f2d5dedfa2d00f"}},{"code_sha256_prefix":"c274c52d4709e336","entry":"calculate_hit_rate_on_sparse_target","repo":"kumo-ai/ContextGNN","repo_kind":"official","path":"contextgnn/utils/metrics.py","file_url":"https://github.com/kumo-ai/ContextGNN/blob/HEAD/contextgnn/utils/metrics.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":"c274c52d4709e336"}},{"code_sha256_prefix":"2fa173e988b208d2","entry":"loss_function","repo":"kumo-ai/ContextGNN","repo_kind":"official","path":"benchmark/relbench_multi_vae.py","file_url":"https://github.com/kumo-ai/ContextGNN/blob/HEAD/benchmark/relbench_multi_vae.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":"2fa173e988b208d2"}},{"code_sha256_prefix":"d7c1cd833b104e40","entry":"test","repo":"kumo-ai/ContextGNN","repo_kind":"official","path":"benchmark/relbench_link_prediction_benchmark.py","file_url":"https://github.com/kumo-ai/ContextGNN/blob/HEAD/benchmark/relbench_link_prediction_benchmark.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":"d7c1cd833b104e40"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}