{"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/promptmm-multi-modal-knowledge-distillation","title":"PromptMM: Multi-Modal Knowledge Distillation for Recommendation with Prompt-Tuning","arxiv_id":"2402.17188","date":"2024-02-27","proceeding":null,"authors":["Wei Wei","Jiabin Tang","Yangqin Jiang","Lianghao Xia","Chao Huang"],"abstract":"Multimedia online platforms (e.g., Amazon, TikTok) have greatly benefited from the incorporation of multimedia (e.g., visual, textual, and acoustic) content into their personal recommender systems. These modalities provide intuitive semantics that facilitate modality-aware user preference modeling. However, two key challenges in multi-modal recommenders remain unresolved: i) The introduction of multi-modal encoders with a large number of additional parameters causes overfitting, given high-dimensional multi-modal features provided by extractors (e.g., ViT, BERT). ii) Side information inevitably introduces inaccuracies and redundancies, which skew the modality-interaction dependency from reflecting true user preference. To tackle these problems, we propose to simplify and empower recommenders through Multi-modal Knowledge Distillation (PromptMM) with the prompt-tuning that enables adaptive quality distillation. Specifically, PromptMM conducts model compression through distilling u-i edge relationship and multi-modal node content from cumbersome teachers to relieve students from the additional feature reduction parameters. To bridge the semantic gap between multi-modal context and collaborative signals for empowering the overfitting teacher, soft prompt-tuning is introduced to perform student task-adaptive. Additionally, to adjust the impact of inaccuracies in multimedia data, a disentangled multi-modal list-wise distillation is developed with modality-aware re-weighting mechanism. Experiments on real-world data demonstrate PromptMM's superiority over existing techniques. Ablation tests confirm the effectiveness of key components. Additional tests show the efficiency and effectiveness.","url_abs":"https://arxiv.org/abs/2402.17188v3","url_pdf":"https://arxiv.org/pdf/2402.17188v3.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":"promptmm-multi-modal-knowledge-distillation","repo_url":"https://github.com/hkuds/promptmm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"model-compression","task_name":"Model Compression"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.17188","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17188"}},"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/hkuds/promptmm","reach":{"status":"ok"}}],"summary":{"ran":7,"ran_draft_wrong":1,"ran_honours":1,"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":11,"ran":10,"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":11,"samples":[{"code_sha256_prefix":"ea02c0066939a02c","entry":"average_precision","repo":"hkuds/promptmm","repo_kind":"official","path":"codes/utility/metrics.py","file_url":"https://github.com/hkuds/promptmm/blob/HEAD/codes/utility/metrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea02c0066939a02c"}},{"code_sha256_prefix":"37c8ab61f69c3c23","entry":"build_knn_neighbourhood","repo":"hkuds/promptmm","repo_kind":"official","path":"LATTICE/codes/Models.py","file_url":"https://github.com/hkuds/promptmm/blob/HEAD/LATTICE/codes/Models.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"37c8ab61f69c3c23"}},{"code_sha256_prefix":"220cb127bddfb532","entry":"build_knn_normalized_graph","repo":"hkuds/promptmm","repo_kind":"official","path":"codes/utility/norm.py","file_url":"https://github.com/hkuds/promptmm/blob/HEAD/codes/utility/norm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"220cb127bddfb532"}},{"code_sha256_prefix":"e6fb9f69e2c06f0c","entry":"build_sim","repo":"hkuds/promptmm","repo_kind":"official","path":"LATTICE/codes/Models.py","file_url":"https://github.com/hkuds/promptmm/blob/HEAD/LATTICE/codes/Models.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e6fb9f69e2c06f0c"}},{"code_sha256_prefix":"b18055ccb5503f13","entry":"build_sim","repo":"hkuds/promptmm","repo_kind":"official","path":"codes/utility/norm.py","file_url":"https://github.com/hkuds/promptmm/blob/HEAD/codes/utility/norm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b18055ccb5503f13"}},{"code_sha256_prefix":"698d3807a0c41ec9","entry":"compute_normalized_laplacian","repo":"hkuds/promptmm","repo_kind":"official","path":"LATTICE/codes/Models.py","file_url":"https://github.com/hkuds/promptmm/blob/HEAD/LATTICE/codes/Models.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"698d3807a0c41ec9"}},{"code_sha256_prefix":"3f4becfa0b0ec911","entry":"dot","repo":"hkuds/promptmm","repo_kind":"official","path":"codes/Models.py","file_url":"https://github.com/hkuds/promptmm/blob/HEAD/codes/Models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3f4becfa0b0ec911"}},{"code_sha256_prefix":"de0d0e47ac6bbe6c","entry":"precision_at_k","repo":"hkuds/promptmm","repo_kind":"official","path":"codes/utility/metrics.py","file_url":"https://github.com/hkuds/promptmm/blob/HEAD/codes/utility/metrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"de0d0e47ac6bbe6c"}},{"code_sha256_prefix":"4437293713f250ee","entry":"recall","repo":"hkuds/promptmm","repo_kind":"official","path":"codes/utility/metrics.py","file_url":"https://github.com/hkuds/promptmm/blob/HEAD/codes/utility/metrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4437293713f250ee"}},{"code_sha256_prefix":"94aa457af38d3535","entry":"sparse_dropout","repo":"hkuds/promptmm","repo_kind":"official","path":"codes/Models.py","file_url":"https://github.com/hkuds/promptmm/blob/HEAD/codes/Models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"94aa457af38d3535"}},{"code_sha256_prefix":"9ca663afcc4bd067","entry":"get_sparse_laplacian","repo":"hkuds/promptmm","repo_kind":"official","path":"codes/utility/norm.py","file_url":"https://github.com/hkuds/promptmm/blob/HEAD/codes/utility/norm.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9ca663afcc4bd067"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}