{"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/carca-context-and-attribute-aware-next-item","title":"CARCA: Context and Attribute-Aware Next-Item Recommendation via Cross-Attention","arxiv_id":"2204.06519","date":"2022-04-04","proceeding":null,"authors":["Ahmed Rashed","Shereen Elsayed","Lars Schmidt-Thieme"],"abstract":"In sparse recommender settings, users' context and item attributes play a crucial role in deciding which items to recommend next. Despite that, recent works in sequential and time-aware recommendations usually either ignore both aspects or only consider one of them, limiting their predictive performance. In this paper, we address these limitations by proposing a context and attribute-aware recommender model (CARCA) that can capture the dynamic nature of the user profiles in terms of contextual features and item attributes via dedicated multi-head self-attention blocks that extract profile-level features and predicting item scores. Also, unlike many of the current state-of-the-art sequential item recommendation approaches that use a simple dot-product between the most recent item's latent features and the target items embeddings for scoring, CARCA uses cross-attention between all profile items and the target items to predict their final scores. This cross-attention allows CARCA to harness the correlation between old and recent items in the user profile and their influence on deciding which item to recommend next. Experiments on four real-world recommender system datasets show that the proposed model significantly outperforms all state-of-the-art models in the task of item recommendation and achieving improvements of up to 53% in Normalized Discounted Cumulative Gain (NDCG) and Hit-Ratio. Results also show that CARCA outperformed several state-of-the-art dedicated image-based recommender systems by merely utilizing image attributes extracted from a pre-trained ResNet50 in a black-box fashion.","url_abs":"https://arxiv.org/abs/2204.06519v1","url_pdf":"https://arxiv.org/pdf/2204.06519v1.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":"carca-context-and-attribute-aware-next-item","repo_url":"https://github.com/ahmedrashed-ml/carca","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"carca-context-and-attribute-aware-next-item","repo_url":"https://github.com/ariaattar/CASM-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"},{"task_slug":"sequential-recommendation","task_name":"Sequential Recommendation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/recommendation-systems-on-amazon-beauty","task":"Recommendation Systems","dataset":"Amazon Beauty","model":"CARCA","rank_in_archive_order":4,"of":6,"metrics":{"Hit@10":"0.579","nDCG@10":"0.396"},"uses_additional_data":true},{"leaderboard":"/sota/recommendation-systems-on-amazon-fashion","task":"Recommendation Systems","dataset":"Amazon Fashion","model":"CARCA","rank_in_archive_order":2,"of":4,"metrics":{"HitRatio@ 10 (100 Neg. Samples)":"0.591","nDCG@10 (100 Neg. Samples)":"0.381"},"uses_additional_data":true},{"leaderboard":"/sota/recommendation-systems-on-amazon-games","task":"Recommendation Systems","dataset":"Amazon Games","model":"CARCA","rank_in_archive_order":3,"of":6,"metrics":{"Hit@10":"0.7820","nDCG@10":"0.5730"},"uses_additional_data":true},{"leaderboard":"/sota/sequential-recommendation-on-amazon-men","task":"Sequential Recommendation","dataset":"Amazon Men","model":"CARCA","rank_in_archive_order":1,"of":1,"metrics":{"Hit@10":"0.550"},"uses_additional_data":true}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}