{"url":"/task/multi-modal-recommendation","name":"Multi-modal Recommendation","slug":"multi-modal-recommendation","description_markdown":null,"categories":[{"name":"Graphs","url":"/area/graphs"},{"name":"Knowledge Base","url":"/area/knowledge-base"},{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":30,"papers_with_code":18,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/multi-modal-recommendation-on-amazon-baby","slug":"multi-modal-recommendation-on-amazon-baby","dataset":"Amazon Baby","dataset_url":"/dataset/amazon-baby","rows_in_archive":10,"metrics":["NDCG@20"],"first_row_in_archive_order":{"model":"MIG-GT","paper_title":"Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation","paper_url":"/paper/modality-independent-graph-neural-networks","paper_date":"2024-12-18","arxiv_id":"2412.13994","code_links":[{"title":"crawlscript/mig-gt","url":"https://github.com/crawlscript/mig-gt"}],"syntology":null}},{"leaderboard":"/sota/multi-modal-recommendation-on-amazon-clothing","slug":"multi-modal-recommendation-on-amazon-clothing","dataset":"Amazon Clothing","dataset_url":"/dataset/amazon-clothing","rows_in_archive":10,"metrics":["NDCG@20"],"first_row_in_archive_order":{"model":"MIG-GT","paper_title":"Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation","paper_url":"/paper/modality-independent-graph-neural-networks","paper_date":"2024-12-18","arxiv_id":"2412.13994","code_links":[{"title":"crawlscript/mig-gt","url":"https://github.com/crawlscript/mig-gt"}],"syntology":null}},{"leaderboard":"/sota/multi-modal-recommendation-on-amazon-sports","slug":"multi-modal-recommendation-on-amazon-sports","dataset":"Amazon Sports","dataset_url":"/dataset/amazon-sports-1","rows_in_archive":10,"metrics":["NGCG@20"],"first_row_in_archive_order":{"model":"MIG-GT","paper_title":"Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation","paper_url":"/paper/modality-independent-graph-neural-networks","paper_date":"2024-12-18","arxiv_id":"2412.13994","code_links":[{"title":"crawlscript/mig-gt","url":"https://github.com/crawlscript/mig-gt"}],"syntology":null}}],"datasets":[{"url":"/dataset/amazon-sports-1","name":"Amazon Sports","full_name":"Amazon Sports 5-core","num_papers_in_archive":24},{"url":"/dataset/amazon-clothing","name":"Amazon Clothing","full_name":"Amazon Clothing 5-core","num_papers_in_archive":19},{"url":"/dataset/amazon-baby","name":"Amazon Baby","full_name":"Amazon Baby 5-core","num_papers_in_archive":13}],"subtasks":[],"parent_tasks":[{"url":"/task/recommendation-systems","name":"Recommendation Systems"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":18,"of":18,"tagged_in_all":30,"items":[{"url":"/paper/lightgcn-simplifying-and-powering-graph","title":"LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation","date":"2020-02-06","arxiv_id":"2002.02126","repositories_listed":18,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":2}},{"url":"/paper/vbpr-visual-bayesian-personalized-ranking","title":"VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback","date":"2015-10-06","arxiv_id":"1510.01784","repositories_listed":7,"syntology":{"n":28,"n_ran":3,"n_unverified":25,"n_pointer_only":3}},{"url":"/paper/multi-modal-self-supervised-learning-for","title":"Multi-Modal Self-Supervised Learning for Recommendation","date":"2023-02-21","arxiv_id":"2302.10632","repositories_listed":2,"syntology":null},{"url":"/paper/a-tale-of-two-graphs-freezing-and-denoising","title":"A Tale of Two Graphs: Freezing and Denoising Graph Structures for Multimodal Recommendation","date":"2022-11-13","arxiv_id":"2211.06924","repositories_listed":2,"syntology":null},{"url":"/paper/bootstrap-latent-representations-for-multi","title":"Bootstrap Latent Representations for Multi-modal Recommendation","date":"2022-07-13","arxiv_id":"2207.05969","repositories_listed":2,"syntology":null},{"url":"/paper/mgdcf-distance-learning-via-markov-graph","title":"MGDCF: Distance Learning via Markov Graph Diffusion for Neural Collaborative Filtering","date":"2022-04-05","arxiv_id":"2204.02338","repositories_listed":2,"syntology":null},{"url":"/paper/rag-visualrec-an-open-resource-for-vision-and","title":"RAG-VisualRec: An Open Resource for Vision- and Text-Enhanced Retrieval-Augmented Generation in Recommendation","date":"2025-06-25","arxiv_id":"2506.20817","repositories_listed":1,"syntology":null},{"url":"/paper/teach-me-how-to-denoise-a-universal-framework","title":"Teach Me How to Denoise: A Universal Framework for Denoising Multi-modal Recommender Systems via Guided Calibration","date":"2025-04-19","arxiv_id":"2504.14214","repositories_listed":1,"syntology":null},{"url":"/paper/modality-independent-graph-neural-networks","title":"Modality-Independent Graph Neural Networks with Global Transformers for Multimodal Recommendation","date":"2024-12-18","arxiv_id":"2412.13994","repositories_listed":1,"syntology":null},{"url":"/paper/harnessing-multimodal-large-language-models","title":"Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation","date":"2024-08-19","arxiv_id":"2408.09698","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/towards-bridging-the-cross-modal-semantic-gap","title":"Towards Bridging the Cross-modal Semantic Gap for Multi-modal Recommendation","date":"2024-07-07","arxiv_id":"2407.05420","repositories_listed":1,"syntology":null},{"url":"/paper/umair-fps-user-aware-multi-modal-animation","title":"UMAIR-FPS: User-aware Multi-modal Animation Illustration Recommendation Fusion with Painting Style","date":"2024-02-16","arxiv_id":"2402.10381","repositories_listed":1,"syntology":null},{"url":"/paper/online-distillation-enhanced-multi-modal","title":"Online Distillation-enhanced Multi-modal Transformer for Sequential Recommendation","date":"2023-08-08","arxiv_id":"2308.04067","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-learning-for-multimedia","title":"Self-Supervised Learning for Multimedia Recommendation","date":"2022-06-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dualgnn-dual-graph-neural-network-for","title":"DualGNN: Dual Graph Neural Network for Multimedia Recommendation","date":"2021-12-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/grcn-graph-refined-convolutional-network-for","title":"GRCN: Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback","date":"2021-11-03","arxiv_id":"2111.02036","repositories_listed":1,"syntology":null},{"url":"/paper/mining-latent-structures-for-multimedia","title":"Mining Latent Structures for Multimedia Recommendation","date":"2021-04-19","arxiv_id":"2104.09036","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/mmgcn-multi-modal-graph-convolution-network","title":"MMGCN: Multi-modal Graph Convolution Network for Personalized Recommendation of Micro-video","date":"2019-10-19","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}