{"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/i2moe-interpretable-multimodal-interaction","title":"I2MoE: Interpretable Multimodal Interaction-aware Mixture-of-Experts","arxiv_id":"2505.19190","date":"2025-05-25","proceeding":null,"authors":["Jiayi Xin","Sukwon Yun","Jie Peng","Inyoung Choi","Jenna L. Ballard","Tianlong Chen","Qi Long"],"abstract":"Modality fusion is a cornerstone of multimodal learning, enabling information integration from diverse data sources. However, vanilla fusion methods are limited by (1) inability to account for heterogeneous interactions between modalities and (2) lack of interpretability in uncovering the multimodal interactions inherent in the data. To this end, we propose I2MoE (Interpretable Multimodal Interaction-aware Mixture of Experts), an end-to-end MoE framework designed to enhance modality fusion by explicitly modeling diverse multimodal interactions, as well as providing interpretation on a local and global level. First, I2MoE utilizes different interaction experts with weakly supervised interaction losses to learn multimodal interactions in a data-driven way. Second, I2MoE deploys a reweighting model that assigns importance scores for the output of each interaction expert, which offers sample-level and dataset-level interpretation. Extensive evaluation of medical and general multimodal datasets shows that I2MoE is flexible enough to be combined with different fusion techniques, consistently improves task performance, and provides interpretation across various real-world scenarios. Code is available at https://github.com/Raina-Xin/I2MoE.","url_abs":"https://arxiv.org/abs/2505.19190v1","url_pdf":"https://arxiv.org/pdf/2505.19190v1.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":"i2moe-interpretable-multimodal-interaction","repo_url":"https://github.com/raina-xin/i2moe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"multimodal-interaction","task_name":"multimodal interaction"}],"methods":[{"method_slug":"moe","method_name":"MoE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.19190","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19190"}},"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":"deterministic:regex_extraction","url":"https://github.com/Raina-Xin/I2MoE","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/raina-xin/i2moe","reach":{"status":"ok"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"658349de1f7c6cf1","entry":"InteractionExpert","repo":"raina-xin/i2moe","repo_kind":"official","path":"src/imoe/InteractionMoE.py","file_url":"https://github.com/raina-xin/i2moe/blob/HEAD/src/imoe/InteractionMoE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"658349de1f7c6cf1"}},{"code_sha256_prefix":"50784974ad2c41ca","entry":"InteractionMoE","repo":"raina-xin/i2moe","repo_kind":"official","path":"src/imoe/InteractionMoE.py","file_url":"https://github.com/raina-xin/i2moe/blob/HEAD/src/imoe/InteractionMoE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"50784974ad2c41ca"}},{"code_sha256_prefix":"f16c04f948320e48","entry":"MLP","repo":"raina-xin/i2moe","repo_kind":"official","path":"src/imoe/InteractionMoE.py","file_url":"https://github.com/raina-xin/i2moe/blob/HEAD/src/imoe/InteractionMoE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f16c04f948320e48"}},{"code_sha256_prefix":"5662d82252ed1434","entry":"MLPReWeighting","repo":"raina-xin/i2moe","repo_kind":"official","path":"src/imoe/InteractionMoE.py","file_url":"https://github.com/raina-xin/i2moe/blob/HEAD/src/imoe/InteractionMoE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5662d82252ed1434"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}