CA3195441A1 - Systemes et procedes de fourniture fonction de perte modifiee dans un apprentissage federe/divise - Google Patents

Systemes et procedes de fourniture fonction de perte modifiee dans un apprentissage federe/divise

Info

Publication number
CA3195441A1
CA3195441A1 CA3195441A CA3195441A CA3195441A1 CA 3195441 A1 CA3195441 A1 CA 3195441A1 CA 3195441 A CA3195441 A CA 3195441A CA 3195441 A CA3195441 A CA 3195441A CA 3195441 A1 CA3195441 A1 CA 3195441A1
Authority
CA
Canada
Prior art keywords
client
server
client system
model
server system
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CA3195441A
Other languages
English (en)
Inventor
Gharib GHARIBI
Ravi PATEL
Babak Poorebrahim GILKALAYE
Praneeth Vepakomma
Greg STORM
Riddhiman Das
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
TripleBlind Inc
Original Assignee
TripleBlind Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by TripleBlind Inc filed Critical TripleBlind Inc
Priority claimed from US17/499,153 external-priority patent/US11431688B2/en
Publication of CA3195441A1 publication Critical patent/CA3195441A1/fr
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Storage Device Security (AREA)

Abstract

L'invention concerne un procédé qui comprend l'entraînement, au niveau d'un client, d'une partie d'un réseau d'apprentissage profond jusqu'à une couche divisée du client. En fonction d'une sortie de la couche divisée, le procédé comprend la réalisation, au niveau d'un serveur, de l'entraînement du réseau d'apprentissage profond par la propagation directe de la sortie reçue au niveau d'une couche divisée du serveur vers une dernière couche du serveur. Le serveur calcule une fonction de perte pondérée pour le client au niveau de la dernière couche et stocke la fonction de perte calculée. Après le stockage de la fonction de perte respective de chaque client respectif d'une pluralité de clients, le serveur calcule la moyenne de la pluralité de fonctions de perte de client pondérées respectives et effectue la rétropropagation des gradients en fonction de la valeur de perte moyenne de la dernière couche du serveur dans la couche divisée du serveur et transmet uniquement les gradients de couche divisée de serveur aux clients respectifs.
CA3195441A 2020-10-13 2021-10-12 Systemes et procedes de fourniture fonction de perte modifiee dans un apprentissage federe/divise Pending CA3195441A1 (fr)

Applications Claiming Priority (7)

Application Number Priority Date Filing Date Title
US202063090904P 2020-10-13 2020-10-13
US63/090,904 2020-10-13
US202163226135P 2021-07-27 2021-07-27
US63/226,135 2021-07-27
US17/499,153 2021-10-12
US17/499,153 US11431688B2 (en) 2019-12-13 2021-10-12 Systems and methods for providing a modified loss function in federated-split learning
PCT/US2021/054518 WO2022081539A1 (fr) 2020-10-13 2021-10-12 Systèmes et procédés de fourniture fonction de perte modifiée dans un apprentissage fédéré/divisé

Publications (1)

Publication Number Publication Date
CA3195441A1 true CA3195441A1 (fr) 2022-04-21

Family

ID=81208549

Family Applications (1)

Application Number Title Priority Date Filing Date
CA3195441A Pending CA3195441A1 (fr) 2020-10-13 2021-10-12 Systemes et procedes de fourniture fonction de perte modifiee dans un apprentissage federe/divise

Country Status (2)

Country Link
CA (1) CA3195441A1 (fr)
WO (1) WO2022081539A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115545172B (zh) * 2022-11-29 2023-02-07 支付宝(杭州)信息技术有限公司 兼顾隐私保护和公平性的图神经网络的训练方法及装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9984337B2 (en) * 2014-10-08 2018-05-29 Nec Corporation Parallelized machine learning with distributed lockless training
US10755172B2 (en) * 2016-06-22 2020-08-25 Massachusetts Institute Of Technology Secure training of multi-party deep neural network

Also Published As

Publication number Publication date
WO2022081539A1 (fr) 2022-04-21

Similar Documents

Publication Publication Date Title
US11431688B2 (en) Systems and methods for providing a modified loss function in federated-split learning
US20220021662A1 (en) Operating system for blockchain iot devices
TWI770022B (zh) 電腦實施之控制方法、系統及控制系統
US12073387B2 (en) System and method of multi-round token distribution using a blockchain network
US11991156B2 (en) Systems and methods for secure averaging of models for federated learning and blind learning using secure multi-party computation
Cao et al. A federated deep learning framework for privacy preservation and communication efficiency
CN113722753A (zh) 基于区块链的隐私数据处理方法、装置及系统
CA3195441A1 (fr) Systemes et procedes de fourniture fonction de perte modifiee dans un apprentissage federe/divise
AU2019389028A1 (en) Multi-hop security amplification
EP3379408B1 (fr) Fonctions aléatoires actualisables
EP4229559A1 (fr) Systèmes et procédés de fourniture fonction de perte modifiée dans un apprentissage fédéré/divisé
CN115361196A (zh) 一种基于区块链网络的业务交互方法
Simporé Controllability of a family of nonlinear population dynamics models
Piotrowski et al. Towards a Secure Peer-to-Peer Federated Learning Framework
Hwang et al. Quantum entanglement establishment between two strangers
Rahmani et al. Secure two-party computation via measurement-based quantum computing
CN115510466A (zh) 密文预测方法、相关装置及存储介质