{"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/a-framework-for-multi-modal-learning-jointly","title":"Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning","arxiv_id":"2405.17613","date":"2024-05-27","proceeding":null,"authors":["Divyam Madaan","Taro Makino","Sumit Chopra","Kyunghyun Cho"],"abstract":"Supervised multi-modal learning involves mapping multiple modalities to a target label. Previous studies in this field have concentrated on capturing in isolation either the inter-modality dependencies (the relationships between different modalities and the label) or the intra-modality dependencies (the relationships within a single modality and the label). We argue that these conventional approaches that rely solely on either inter- or intra-modality dependencies may not be optimal in general. We view the multi-modal learning problem from the lens of generative models where we consider the target as a source of multiple modalities and the interaction between them. Towards that end, we propose inter- & intra-modality modeling (I2M2) framework, which captures and integrates both the inter- and intra-modality dependencies, leading to more accurate predictions. We evaluate our approach using real-world healthcare and vision-and-language datasets with state-of-the-art models, demonstrating superior performance over traditional methods focusing only on one type of modality dependency.","url_abs":"https://arxiv.org/abs/2405.17613v2","url_pdf":"https://arxiv.org/pdf/2405.17613v2.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":"a-framework-for-multi-modal-learning-jointly","repo_url":"https://github.com/divyam3897/i2m2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.17613","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17613"}},"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/divyam3897/i2m2","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":4},"by_repo_kind":{"official":{"samples":11,"ran":7,"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":"809e3aa9964cb3ea","entry":"AUPRC","repo":"divyam3897/i2m2","repo_kind":"official","path":"avmnist_and_mimic/eval_scripts/performance.py","file_url":"https://github.com/divyam3897/i2m2/blob/HEAD/avmnist_and_mimic/eval_scripts/performance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"809e3aa9964cb3ea"}},{"code_sha256_prefix":"0e748b3eca1dc04c","entry":"center_crop","repo":"divyam3897/i2m2","repo_kind":"official","path":"fastMRI/models/preactresnet_knee.py","file_url":"https://github.com/divyam3897/i2m2/blob/HEAD/fastMRI/models/preactresnet_knee.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0e748b3eca1dc04c"}},{"code_sha256_prefix":"191c253b532edecf","entry":"f1_score","repo":"divyam3897/i2m2","repo_kind":"official","path":"avmnist_and_mimic/eval_scripts/performance.py","file_url":"https://github.com/divyam3897/i2m2/blob/HEAD/avmnist_and_mimic/eval_scripts/performance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"191c253b532edecf"}},{"code_sha256_prefix":"5df0e36414846c02","entry":"get_robustness_metric","repo":"divyam3897/i2m2","repo_kind":"official","path":"avmnist_and_mimic/eval_scripts/robustness.py","file_url":"https://github.com/divyam3897/i2m2/blob/HEAD/avmnist_and_mimic/eval_scripts/robustness.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5df0e36414846c02"}},{"code_sha256_prefix":"f86744b3991d473e","entry":"getallparams","repo":"divyam3897/i2m2","repo_kind":"official","path":"avmnist_and_mimic/eval_scripts/complexity.py","file_url":"https://github.com/divyam3897/i2m2/blob/HEAD/avmnist_and_mimic/eval_scripts/complexity.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f86744b3991d473e"}},{"code_sha256_prefix":"c93aad3618c35efa","entry":"ptsort","repo":"divyam3897/i2m2","repo_kind":"official","path":"avmnist_and_mimic/eval_scripts/performance.py","file_url":"https://github.com/divyam3897/i2m2/blob/HEAD/avmnist_and_mimic/eval_scripts/performance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c93aad3618c35efa"}},{"code_sha256_prefix":"9990c3a811795e37","entry":"relative_robustness","repo":"divyam3897/i2m2","repo_kind":"official","path":"avmnist_and_mimic/eval_scripts/robustness.py","file_url":"https://github.com/divyam3897/i2m2/blob/HEAD/avmnist_and_mimic/eval_scripts/robustness.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9990c3a811795e37"}},{"code_sha256_prefix":"7ee0d14726bfe8b5","entry":"CreateOp","repo":"divyam3897/i2m2","repo_kind":"official","path":"avmnist_and_mimic/utils/aux_models.py","file_url":"https://github.com/divyam3897/i2m2/blob/HEAD/avmnist_and_mimic/utils/aux_models.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":"7ee0d14726bfe8b5"}},{"code_sha256_prefix":"96037b0c5b8c3511","entry":"PreActResNet18","repo":"divyam3897/i2m2","repo_kind":"official","path":"fastMRI/models/preactresnet_knee.py","file_url":"https://github.com/divyam3897/i2m2/blob/HEAD/fastMRI/models/preactresnet_knee.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":"96037b0c5b8c3511"}},{"code_sha256_prefix":"6031bfde11ce378c","entry":"effective_robustness","repo":"divyam3897/i2m2","repo_kind":"official","path":"avmnist_and_mimic/eval_scripts/robustness.py","file_url":"https://github.com/divyam3897/i2m2/blob/HEAD/avmnist_and_mimic/eval_scripts/robustness.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":"6031bfde11ce378c"}},{"code_sha256_prefix":"ea7f7fe6fcbf481d","entry":"train_model","repo":"divyam3897/i2m2","repo_kind":"official","path":"fastMRI/classifier.py","file_url":"https://github.com/divyam3897/i2m2/blob/HEAD/fastMRI/classifier.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":"ea7f7fe6fcbf481d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}