{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:57:25Z","timestamp":1759334245817,"version":"build-2065373602"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T00:00:00Z","timestamp":1749340800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T00:00:00Z","timestamp":1749340800000},"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":[[2025,6,8]]},"DOI":"10.1109\/icc52391.2025.11161206","type":"proceedings-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T17:34:55Z","timestamp":1758908095000},"page":"5356-5361","source":"Crossref","is-referenced-by-count":0,"title":["MegaMon: Transformer-Based Network Traffic Monitor and Analysis for LLM Training"],"prefix":"10.1109","author":[{"given":"Qi","family":"Xin","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxiang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Beijing University of Posts and Telecommunications,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongyue","family":"Zhang","sequence":"additional","affiliation":[{"name":"China Unicom Research Institute,Next Generation Internet Research Department,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bowen","family":"Han","sequence":"additional","affiliation":[{"name":"China Unicom Research Institute,Next Generation Internet Research Department,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bohua","family":"Xu","sequence":"additional","affiliation":[{"name":"China Unicom Research Institute,Next Generation Internet Research Department,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A Survey of Large Language Models","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672265"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3278532.3278566"},{"key":"ref4","first-page":"1","article-title":"Efficient large-scale language model training on GPU clusters using Megatron-LM","volume-title":"Proc. Int. Conf. High Perform. Comput., Netw., Storage Anal.","author":"Narayanan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605613"},{"key":"ref6","article-title":"Boosting Large-scale Parallel Training Efficiency with C4: A Communication-Driven Approach","author":"Dong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","first-page":"745","article-title":"MegaScale: Scaling large language model training to more than 10,000 GPUs","volume-title":"Proc. 21st USENIX Symp. Netw. Syst. Design Implementation (NSDI)","author":"Jiang","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672233"},{"issue":"112","key":"ref9","first-page":"1","article-title":"Measuring the effects of data parallelism on neural network training","volume":"20","author":"Shallue","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","article-title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","author":"Shoeybi","year":"2020","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.14778\/3514061.3514067"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3424945"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/ifipnetworking55013.2022.9829764"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2019.2927886"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-023-2894-6"},{"key":"ref17","article-title":"LLM as Runtime Error Handler: A Promising Pathway to Adaptive Self-Healing of Software Systems","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3236367.3236381"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2966884.2966912"},{"key":"ref20","article-title":"iTransformer: Inverted transformers are effective for time series forecasting","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446307"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446883"},{"key":"ref23","article-title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","author":"Nie","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Deep Transformer Models for Time Series Forecasting: The Influenza Prevalence Case","author":"Wu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref26","article-title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","author":"Bai","year":"2018","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume":"28","author":"Shi","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1953.tb01433.x"},{"key":"ref30","article-title":"Llama2: Open Foundation and Fine-Tuned Chat Models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"volume-title":"NVIDIA Collective Communications Library (NCCL)","year":"2024","key":"ref31"},{"volume-title":"Infrawaves Official Website","year":"2024","author":"Hu","key":"ref32"}],"event":{"name":"ICC 2025 - IEEE International Conference on Communications","start":{"date-parts":[[2025,6,8]]},"location":"Montreal, QC, Canada","end":{"date-parts":[[2025,6,12]]}},"container-title":["ICC 2025 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11160703\/11160705\/11161206.pdf?arnumber=11161206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:24:55Z","timestamp":1759238695000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11161206\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,8]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icc52391.2025.11161206","relation":{},"subject":[],"published":{"date-parts":[[2025,6,8]]}}}