Fast adaptation of multi-task meta-learning for optical performance monitoring

计算机科学 梯度下降 人工智能 算法 人工神经网络
作者
Yu Zhang,Peng Zhou,Yan Liu,Jixiang Wang,Chuanqi Li,Ye Lu
出处
期刊:Optics Express [Optica Publishing Group]
卷期号:31 (14): 23183-23183 被引量:12
标识
DOI:10.1364/oe.488829
摘要

An algorithm is proposed for few-shot-learning (FSL) jointing modulation format identification (MFI) and optical signal-to-noise ratio (OSNR) estimation. The constellation diagrams of six widely-used modulation formats over a wide range of OSNR (10-40 dB) are obtained by a dual-polarization (DP) coherent detection system at 32 GBaud. We introduce auxiliary task to model-agnostic meta-learning (MAML) which makes the gradient of meta tasks decline faster in the direction of optimal target. Ablation experiments including multi-task model-agnostic meta-learning (MT-MAML), single-task model-agnostic meta-learning (ST-MAML) and adaptive multi-task learning (AMTL) are executed to train a data set with only 20 examples for each class. First, we discuss the impact from the number of shots and gradient descent steps for support set on the meta-learning based schemes to determine the best hyper parameters and conclude that the proposed method better captures the similarity between new and previous knowledge at 4 shot and 1 step. Withdrawn fine-tuning, the model achieves the lowest error ∼0.37 dB initially. Then, we simulate two other schemes (AMTL and ST-MAML), and the numerical results shows that mean square error (MSE) are ∼0.6 dB, ∼0.3 dB and ∼0.18 dB, respectively, proposed method has faster adaption to main task. For low order modulation formats, the proposed method almost reduces the error to 0. Meanwhile, we reveal the degree of deviation between the prediction and target and find that the deviation is mainly concentrated in the high OSNR range of 25-40 dB. Specifically, we investigate the variation curve of adaptive weights during pretraining and conclude that after 30 epoch, the model's attention was almost entirely focused on estimating OSNR. In addition, we study the generalization ability of the model by varying the transmission distance. Importantly, excellent generalization is also experimentally verified. In this paper, the method proposed will greatly reduce the cost for repetitively collecting data and the training resources required for fine-tuning models when OPM devices need to be deployed at massive nodes in dynamic optical networks.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
yolanda发布了新的文献求助10
刚刚
jinyu发布了新的文献求助10
1秒前
请问发布了新的文献求助10
2秒前
Ava应助和谐的傥采纳,获得10
2秒前
哈哈王子完成签到,获得积分10
3秒前
朱文韬发布了新的文献求助10
3秒前
WMYY发布了新的文献求助10
4秒前
慕青应助weiwei采纳,获得10
5秒前
5秒前
狗妹那塞完成签到,获得积分10
5秒前
酷波er应助jinyu采纳,获得30
8秒前
8秒前
CY发布了新的文献求助30
12秒前
kelexh发布了新的文献求助10
12秒前
13秒前
13秒前
16秒前
weiwei发布了新的文献求助10
17秒前
皖医梁朝伟完成签到 ,获得积分10
18秒前
dajiejie完成签到 ,获得积分10
18秒前
shw完成签到,获得积分10
19秒前
舒适的秋尽完成签到,获得积分10
20秒前
zzn发布了新的文献求助10
20秒前
lv发布了新的文献求助10
21秒前
21秒前
年三月完成签到 ,获得积分10
23秒前
24秒前
请问发布了新的文献求助10
24秒前
26秒前
失眠的血茗完成签到,获得积分10
26秒前
28秒前
自由发布了新的文献求助10
28秒前
letter完成签到,获得积分10
28秒前
奋斗慕凝完成签到 ,获得积分10
29秒前
爆米花应助魔幻罡采纳,获得10
29秒前
31秒前
烟花应助一一采纳,获得10
37秒前
LHT完成签到,获得积分10
38秒前
lv完成签到,获得积分10
39秒前
高分求助中
【此为提示信息,请勿应助】请按要求发布求助,避免被关 20000
ISCN 2024 – An International System for Human Cytogenomic Nomenclature (2024) 3000
Continuum Thermodynamics and Material Modelling 2000
Encyclopedia of Geology (2nd Edition) 2000
105th Edition CRC Handbook of Chemistry and Physics 1600
Maneuvering of a Damaged Navy Combatant 650
Mixing the elements of mass customisation 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3777922
求助须知:如何正确求助?哪些是违规求助? 3323546
关于积分的说明 10214842
捐赠科研通 3038738
什么是DOI,文献DOI怎么找? 1667634
邀请新用户注册赠送积分活动 798236
科研通“疑难数据库(出版商)”最低求助积分说明 758315