{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T02:32:17Z","timestamp":1775788337314,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T00:00:00Z","timestamp":1716163200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,20]]},"DOI":"10.1109\/infocom52122.2024.10621164","type":"proceedings-article","created":{"date-parts":[[2024,8,12]],"date-time":"2024-08-12T17:25:41Z","timestamp":1723483541000},"page":"611-620","source":"Crossref","is-referenced-by-count":23,"title":["Titanic: Towards Production Federated Learning with Large Language Models"],"prefix":"10.1109","author":[{"given":"Ningxin","family":"Su","sequence":"first","affiliation":[{"name":"University of Toronto,Department of Electrical and Computer Engineering"}]},{"given":"Chenghao","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Toronto,Department of Electrical and Computer Engineering"}]},{"given":"Baochun","family":"Li","sequence":"additional","affiliation":[{"name":"University of Toronto,Department of Electrical and Computer Engineering"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Department of Computer Science and Engineering"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","author":"Touvron","year":"2023"},{"key":"ref2","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Hu"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2018.05.003"},{"key":"ref4","article-title":"Split Learning for Health: Distributed Deep Learning without Sharing Raw Patient Data","volume-title":"Proc. the ICLR AI for Social Good Workshop","author":"Vepakomma"},{"key":"ref5","article-title":"Large Language Models: A New Moore\u2019s Law?","author":"Simon","year":"2021"},{"key":"ref6","first-page":"1273","article-title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","volume-title":"Proc. 20th Int\u2019l Conference on Artificial Intelligence and Statistics (AISTATS)","author":"McMahan"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20825"},{"key":"ref8","first-page":"19","article-title":"Oort: Efficient Federated Learning via Guided Participant Selection","volume-title":"Proc. 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Lai"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/345063.339337"},{"key":"ref10","first-page":"68","article-title":"Incentives Build Robustness in BitTorrent","volume-title":"Proc. Workshop on Economics of Peer-to-Peer Systems","volume":"6","author":"Cohen"},{"key":"ref11","article-title":"Peer-to-Peer Federated Learning on Graphs","author":"Lalitha","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3222971"},{"key":"ref13","article-title":"WebRTC: Real-Time Communication in Browsers","author":"Jennings","year":"2023"},{"key":"ref14","article-title":"Communication Efficiency in Federated Learning: Achievements and Challenges","author":"Shahid","year":"2021"},{"key":"ref15","article-title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","author":"Shoeybi","year":"2020"},{"key":"ref16","article-title":"GPipe: Efficient Training of Giant Neural Networks Using Pipeline Parallelism","volume-title":"Proc. 33rd International Conference on Neural Information Processing Systems (NeurIPS)","author":"Huang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref18","volume-title":"NVIDIA Collective Communications Library (NCCL)","year":"2023"},{"key":"ref19","volume-title":"Open LLM Leaderboard","year":"2023"},{"key":"ref20","article-title":"On the Optimal Assignment of Conference Papers to Reviewers","volume-title":"Dept. Computer and Info. Sci., Univ. of PA, tech. rep. MS-CIS-08-30","author":"Taylor","year":"2008"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/0315059"},{"key":"ref22","article-title":"OPT: Open Pre-trained Transformer Language Models","author":"Zhang","year":"2022"},{"key":"ref23","article-title":"Bloom: A 176B-Parameter Open-Access Multilingual Language Model","author":"Scao","year":"2022"},{"key":"ref24","article-title":"Pointer Sentinel Mixture Models","author":"Merity","year":"2016"}],"event":{"name":"IEEE INFOCOM 2024 - IEEE Conference on Computer Communications","location":"Vancouver, BC, Canada","start":{"date-parts":[[2024,5,20]]},"end":{"date-parts":[[2024,5,23]]}},"container-title":["IEEE INFOCOM 2024 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10621050\/10621073\/10621164.pdf?arnumber=10621164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T05:24:08Z","timestamp":1723526648000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10621164\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,20]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/infocom52122.2024.10621164","relation":{},"subject":[],"published":{"date-parts":[[2024,5,20]]}}}