BR112022011012A2 - Modelos de mistura federada - Google Patents

Modelos de mistura federada

Info

Publication number
BR112022011012A2
BR112022011012A2 BR112022011012A BR112022011012A BR112022011012A2 BR 112022011012 A2 BR112022011012 A2 BR 112022011012A2 BR 112022011012 A BR112022011012 A BR 112022011012A BR 112022011012 A BR112022011012 A BR 112022011012A BR 112022011012 A2 BR112022011012 A2 BR 112022011012A2
Authority
BR
Brazil
Prior art keywords
machine learning
models
learning model
processing device
federed
Prior art date
Application number
BR112022011012A
Other languages
English (en)
Inventor
Reisser Matthias
Welling Max
Gavves Efstratios
Louizos Christos
Original Assignee
Qualcomm Technologies 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 Qualcomm Technologies Inc filed Critical Qualcomm Technologies Inc
Publication of BR112022011012A2 publication Critical patent/BR112022011012A2/pt

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound

Landscapes

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

Abstract

MODELOS DE MISTURA FEDERADA. Os aspectos descritos neste documento fornecem um método de processamento de dados, incluindo: receber um conjunto de parâmetros globais para uma pluralidade de modelos de aprendizado de máquina; processar dados armazenados localmente em um dispositivo de processamento com a pluralidade de modelos de aprendizado de máquina de acordo com o conjunto de parâmetros globais para gerar uma saída de modelo de aprendizado de máquina; receber, no dispositivo de processamento, feedback de usuário em relação à saída de modelo de aprendizado de máquina para a pluralidade de modelos de aprendizado de máquina; realizar uma otimização da pluralidade de modelos de aprendizado de máquina com base na saída de aprendizado de máquina e no feedback de usuário para gerar parâmetros de modelo de aprendizado de máquina atualizados localmente; enviar os parâmetros de modelo de aprendizado de máquina atualizados localmente para um dispositivo de processamento remoto; e receber um conjunto de parâmetros de modelo de aprendizado de máquina atualizados globalmente para a pluralidade de modelos de aprendizado de máquina.
BR112022011012A 2019-12-13 2020-12-14 Modelos de mistura federada BR112022011012A2 (pt)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
GR20190100556 2019-12-13
PCT/US2020/064889 WO2021119601A1 (en) 2019-12-13 2020-12-14 Federated mixture models

Publications (1)

Publication Number Publication Date
BR112022011012A2 true BR112022011012A2 (pt) 2022-08-16

Family

ID=74175956

Family Applications (1)

Application Number Title Priority Date Filing Date
BR112022011012A BR112022011012A2 (pt) 2019-12-13 2020-12-14 Modelos de mistura federada

Country Status (7)

Country Link
US (1) US20230036702A1 (pt)
EP (1) EP4073714A1 (pt)
JP (1) JP2023505973A (pt)
KR (1) KR20220112766A (pt)
CN (1) CN114787824A (pt)
BR (1) BR112022011012A2 (pt)
WO (1) WO2021119601A1 (pt)

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11842260B2 (en) * 2020-09-25 2023-12-12 International Business Machines Corporation Incremental and decentralized model pruning in federated machine learning
US11790039B2 (en) * 2020-10-29 2023-10-17 EMC IP Holding Company LLC Compression switching for federated learning
CN113516249B (zh) * 2021-06-18 2023-04-07 重庆大学 基于半异步的联邦学习方法、系统、服务器及介质
CN113435537B (zh) * 2021-07-16 2022-08-26 同盾控股有限公司 基于Soft GBDT的跨特征联邦学习方法、预测方法
US11443245B1 (en) * 2021-07-22 2022-09-13 Alipay Labs (singapore) Pte. Ltd. Method and system for federated adversarial domain adaptation
JPWO2023032637A1 (pt) * 2021-08-31 2023-03-09
US20230117768A1 (en) * 2021-10-15 2023-04-20 Kiarash SHALOUDEGI Methods and systems for updating optimization parameters of a parameterized optimization algorithm in federated learning
WO2023088531A1 (en) * 2021-11-16 2023-05-25 Huawei Technologies Co., Ltd. Management entity, network element, system, and methods for supporting anomaly detection for communication networks
EP4296909A1 (de) * 2022-06-22 2023-12-27 Siemens Aktiengesellschaft Individuelle testmodelle für generalisierte maschinelle lernmodelle
KR102573880B1 (ko) * 2022-07-21 2023-09-06 고려대학교 산학협력단 다중-너비 인공신경망에 기반한 연합 학습 시스템 및 연합 학습 방법
CN116597672B (zh) * 2023-06-14 2024-02-13 南京云创大数据科技股份有限公司 基于多智能体近端策略优化算法的区域信号灯控制方法
CN117009095B (zh) * 2023-10-07 2024-01-02 湘江实验室 一种隐私数据处理模型生成方法、装置、终端设备及介质
CN117408330B (zh) * 2023-12-14 2024-03-15 合肥高维数据技术有限公司 面向非独立同分布数据的联邦知识蒸馏方法及装置
CN117575291B (zh) * 2024-01-15 2024-05-10 湖南科技大学 基于边缘参数熵的联邦学习的数据协同管理方法

Also Published As

Publication number Publication date
CN114787824A (zh) 2022-07-22
JP2023505973A (ja) 2023-02-14
KR20220112766A (ko) 2022-08-11
EP4073714A1 (en) 2022-10-19
US20230036702A1 (en) 2023-02-02
WO2021119601A1 (en) 2021-06-17

Similar Documents

Publication Publication Date Title
BR112022011012A2 (pt) Modelos de mistura federada
EP3743832A4 (en) GENERATION OF NATURAL LANGUAGE RECOMMENDATIONS BASED ON AN ARTIFICIAL LANGUAGE MODEL
EP4242822A3 (en) Ensuring reproducibility in an artificial intelligence infrastructure
CO2017007032A2 (es) Actualización de modelos de clasificador de entendimiento de lenguaje para un asistente digital personal basándose en externalización masiva
EP4329255A3 (en) Live updating of machine learning models
WO2018213530A3 (en) TRANSLATION BASED ON A NEURONAL NETWORK OF NATURAL LANGUAGE INTERROGATIONS IN DATABASE INTERROGATIONS
MX2017002723A (es) Sistema y metodo para la colaboracion humano - maquina flexible.
WO2016164680A3 (en) Automated model development process
GB2571841A (en) Automated mutual improvement of oilfield models
AU2017246545A1 (en) Selection of machine learning alogorithms
GB2524934A (en) Method and apparatus for document planning
GB2579789A (en) Runtime parameter selection in simulations
EP4242892A3 (en) Code pointer authentication for hardware flow control
BR112018006288A2 (pt) retropropagação seletiva
EP3029535A3 (en) P&ID and control system synchronization
MX2016012272A (es) Intencion de cliente en entorno de busqueda integrada.
CO2019014715A2 (es) Aparato de comunicación, método y programa informático
BR112022010012A2 (pt) Sistemas e métodos para geração automática de modelo
BR112019001236A2 (pt) sistemas e métodos para a execução de um funcionamento suplementar para uma consulta de linguagem natural
WO2019067471A3 (en) Systems and methods for conducting in-situ monitoring in additive manufacture
EP3525100A3 (en) Framework for developing and deploying applications
MY189491A (en) Database data modification request processing method and apparatus
MX2020013214A (es) Actualizacion de graficos ejecutables.
GB2562905A (en) Method for operating energy consumption metering system and energy consumption metering system
JP2017523536A5 (pt)