{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T13:48:57Z","timestamp":1774014537684,"version":"3.50.1"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018859","name":"Tamkeen","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018859","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018859","name":"Tamkeen","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018859","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018859","name":"Tamkeen","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018859","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228348","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-9","source":"Crossref","is-referenced-by-count":1,"title":["MILES: Modality-Informed Learning Rate Scheduler for Balancing Multimodal Learning"],"prefix":"10.1109","author":[{"given":"Alejandro","family":"Guerra-Manzanares","sequence":"first","affiliation":[{"name":"New York University Abu Dhabi,Division of Engineering,Abu Dhabi,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farah E.","family":"Shamout","sequence":"additional","affiliation":[{"name":"New York University Abu Dhabi,Division of Engineering,Abu Dhabi,UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2013.0302"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-06237-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2307\/2554954"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/0-306-47565-0_10"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.02.003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref7","first-page":"24043","article-title":"Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks","volume-title":"International Conference on Machine Learning","author":"Wu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00341-z"},{"key":"ref9","first-page":"9226","article-title":"Modality competition: What makes joint training of multi-modal network fail in deep learning?(provably)","volume-title":"International conference on machine learning","author":"Huang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41299-9_32"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.143"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref14","article-title":"MIND: Modality-informed knowledge distillation framework for multimodal clinical prediction tasks","volume-title":"Transactions on Machine Learning Research","author":"Guerra-Manzanares","year":"2025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref16","article-title":"Written and spoken digits database for multimodal learning","author":"Khacef","year":"2019"},{"key":"ref17","article-title":"The mnist database of handwritten digits","author":"LeCun","year":"1998"},{"key":"ref18","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730302"},{"key":"ref20","article-title":"Gated multimodal units for information fusion","author":"Arevalo","year":"2017"},{"key":"ref21","first-page":"2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Kenton"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","location":"Rome, Italy","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228348.pdf?arnumber=11228348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:47:55Z","timestamp":1763192875000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228348\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228348","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}