Federated Learning with Spiking Neural Networks in Heterogeneous Systems

被引：0

作者：

Tumpa, Sadia Anjum ^{[1
]}

Singh, Sonali ^{[1
]}

Khan, Md Fahim Faysal ^{[1
]}

Kandemir, Mahmut Tylan ^{[1
]}

Narayanan, Vijaykrishnan ^{[1
]}

Das, Chita R. ^{[1
]}

机构：

[1] Penn State Univ, Sch Elect Engn & Comp Sci, University Pk, PA 16802 USA

来源：

2023 IEEE COMPUTER SOCIETY ANNUAL SYMPOSIUM ON VLSI, ISVLSI | 2023年

基金：

美国国家科学基金会;

关键词：

Federated Learning; Neuromorphic Computing; Spiking Neural Network (SNN); Heterogeneous Systems; Internet of Things;

D O I：

10.1109/ISVLSI59464.2023.10238618

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

With the advances in IoT and edge-computing, Federated Learning is ever more popular as it offers data privacy. Low-power spiking neural networks (SNN) are ideal candidates for local nodes in such federated setup. Most prior works assume that the participating nodes have uniform compute resources, which may not be practical. In this work, we propose a federated SNN learning framework for a realistic heterogeneous environment, consisting of nodes with diverse memory-compute capabilities through activation-checkpointing and time-skipping that offers similar to 4x reduction in effective memory requirement for low-memory nodes while improving the accuracy upto 10% for non-independent and identically-distributed data.

引用

页码：49 / 54

页数：6

共 50 条

[1] Federated Learning With Spiking Neural Networks
Venkatesha, Yeshwanth
Kim, Youngeun
Tassiulas, Leandros
Panda, Priyadarshini
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2021, 69 : 6183 - 6194
[2] A Federated Learning Protocol for Spiking Neural Membrane Systems
Plesa, Mihail-Iulian
Gheorghe, Marian
Ipate, Florentin
Zhang, Gexiang
[J]. INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2024,
[3] Efficient asynchronous federated neuromorphic learning of spiking neural networks
Wang, Yuan
Duan, Shukai
Chen, Feng
[J]. NEUROCOMPUTING, 2023, 557
[4] HFedSNN: Efficient Hierarchical Federated Learning using Spiking Neural Networks
Aouedi, Ons
Piamrat, Kandaraj
Sudholt, Mario
[J]. PROCEEDINGS OF THE INT'L ACM SYMPOSIUM ON MOBILITY MANAGEMENT AND WIRELESS ACCESS, MOBIWAC 2023, 2023, : 53 - 60
[5] Federated learning for spiking neural networks by hint-layer knowledge
Xie, Xiurui
Feng, Jingxuan
Liu, Guisong
Zhan, Qiugang
Liu, Zhetong
Zhang, Malu
[J]. APPLIED SOFT COMPUTING, 2024, 163
[6] FedClassAvg: Local Representation Learning for Personalized Federated Learning on Heterogeneous Neural Networks
Jang, Jaehee
Ha, Heonseok
Jung, Dahuin
Yoon, Sungroh
[J]. 51ST INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING, ICPP 2022, 2022,
[7] Federated learning of molecular properties with graph neural networks in a heterogeneous setting
Zhu, Wei
Luo, Jiebo
White, Andrew D.
[J]. PATTERNS, 2022, 3 (06):
[8] FEDERATED NEUROMORPHIC LEARNING OF SPIKING NEURAL NETWORKS FOR LOW-POWER EDGE INTELLIGENCE
Skatchkovsky, Nicolas
Fang, Hyeryung
Simeone, Osvaldo
[J]. 2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 8524 - 8528
[9] Learning to Generalize in Heterogeneous Federated Networks
Chen, Cen
Ye, Tiandi
Wang, Li
Gao, Ming
[J]. PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2022, 2022, : 159 - 168
[10] PerHeFed: A general framework of personalized federated learning for heterogeneous convolutional neural networks
Le Ma
YuYing Liao
Bin Zhou
Wen Xi
[J]. World Wide Web, 2023, 26 : 2027 - 2049

← 1 2 3 4 5 →