DE112020000537T5 - Verbesserung von fairness durch bestärkendes lernen - Google Patents

Verbesserung von fairness durch bestärkendes lernen Download PDF

Info

Publication number
DE112020000537T5
DE112020000537T5 DE112020000537.2T DE112020000537T DE112020000537T5 DE 112020000537 T5 DE112020000537 T5 DE 112020000537T5 DE 112020000537 T DE112020000537 T DE 112020000537T DE 112020000537 T5 DE112020000537 T5 DE 112020000537T5
Authority
DE
Germany
Prior art keywords
fairness
mlm
value
original
computer
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.)
Withdrawn
Application number
DE112020000537.2T
Other languages
German (de)
English (en)
Inventor
Georgios Chaloulos
Frederik Floether
Florian Graf
Patrick Lustenberger
Stefan Ravizza
Eric Slottke
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.)
International Business Machines Corp
Original Assignee
International Business Machines Corp
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 International Business Machines Corp filed Critical International Business Machines Corp
Publication of DE112020000537T5 publication Critical patent/DE112020000537T5/de
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/092—Reinforcement learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/0985—Hyperparameter optimisation; Meta-learning; Learning-to-learn
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Acyclic And Carbocyclic Compounds In Medicinal Compositions (AREA)
DE112020000537.2T 2019-04-08 2020-03-18 Verbesserung von fairness durch bestärkendes lernen Withdrawn DE112020000537T5 (de)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US16/377,727 US20200320428A1 (en) 2019-04-08 2019-04-08 Fairness improvement through reinforcement learning
US16/377,727 2019-04-08
PCT/IB2020/052465 WO2020208444A1 (en) 2019-04-08 2020-03-18 Fairness improvement through reinforcement learning

Publications (1)

Publication Number Publication Date
DE112020000537T5 true DE112020000537T5 (de) 2021-10-21

Family

ID=72663093

Family Applications (1)

Application Number Title Priority Date Filing Date
DE112020000537.2T Withdrawn DE112020000537T5 (de) 2019-04-08 2020-03-18 Verbesserung von fairness durch bestärkendes lernen

Country Status (6)

Country Link
US (1) US20200320428A1 (https=)
JP (1) JP2022527536A (https=)
CN (1) CN113692594A (https=)
DE (1) DE112020000537T5 (https=)
GB (1) GB2597406A (https=)
WO (1) WO2020208444A1 (https=)

Families Citing this family (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11984199B2 (en) * 2019-08-02 2024-05-14 Kpn Innovations, Llc Methods and systems for generating compatible substance instruction sets using artificial intelligence
US11636386B2 (en) * 2019-11-21 2023-04-25 International Business Machines Corporation Determining data representative of bias within a model
US20210201400A1 (en) * 2019-12-27 2021-07-01 Lendingclub Corporation Intelligent servicing
US11556826B2 (en) * 2020-03-20 2023-01-17 Adobe Inc. Generating hyper-parameters for machine learning models using modified Bayesian optimization based on accuracy and training efficiency
US12050975B2 (en) 2020-05-06 2024-07-30 Discover Financial Services System and method for utilizing grouped partial dependence plots and shapley additive explanations in the generation of adverse action reason codes
US12321826B2 (en) 2020-05-06 2025-06-03 Discover Financial Services System and method for utilizing grouped partial dependence plots and game-theoretic concepts and their extensions in the generation of adverse action reason codes
US11551178B2 (en) * 2020-05-14 2023-01-10 Wells Fargo Bank, N.A. Apparatuses and methods for regulation offending model prevention
US12002258B2 (en) * 2020-06-03 2024-06-04 Discover Financial Services System and method for mitigating bias in classification scores generated by machine learning models
US12469075B2 (en) 2020-06-03 2025-11-11 Capital One Financial Corporation Computing system and method for creating a data science model having reduced bias
CN112163677B (zh) * 2020-10-14 2023-09-19 杭州海康威视数字技术股份有限公司 应用机器学习模型的方法、装置及设备
CN112257848B (zh) * 2020-10-22 2024-04-30 北京灵汐科技有限公司 确定逻辑核布局的方法、模型训练方法、电子设备、介质
US12554805B2 (en) 2020-11-27 2026-02-17 Amazon Technologies, Inc. Generating views for bias metrics and feature attribution captured in machine learning pipelines
US12547926B2 (en) 2020-11-27 2026-02-10 Amazon Technologies, Inc. Staged bias measurements in machine learning pipelines
WO2022115402A1 (en) * 2020-11-27 2022-06-02 Amazon Technologies, Inc. Staged bias measurements in machine learning pipelines
US12014287B2 (en) * 2020-12-04 2024-06-18 International Business Machines Corporation Batch scoring model fairness
CN112416602B (zh) * 2020-12-10 2022-09-16 清华大学 一种分布式数据流资源弹性伸缩增强插件及增强方法
CN112905465B (zh) * 2021-02-09 2022-07-22 中国科学院软件研究所 一种基于深度强化学习的机器学习模型黑盒公平性测试方法和系统
US12547673B2 (en) 2021-04-12 2026-02-10 International Business Machines Corporation Calculate fairness of machine learning model
US20220391683A1 (en) * 2021-06-07 2022-12-08 International Business Machines Corporation Bias reduction during artifical intelligence module training
EP4106231A1 (en) * 2021-06-14 2022-12-21 Google LLC Selection of physics-specific model for determination of characteristics of radio frequency signal propagation
US12443676B2 (en) 2021-10-13 2025-10-14 International Business Machines Corporation Controlling a bias of a machine learning module background
US20230222378A1 (en) * 2022-01-07 2023-07-13 Vittorio ROMANIELLO Method and system for evaluating fairness of machine learning model
US20230351172A1 (en) * 2022-04-29 2023-11-02 Intuit Inc. Supervised machine learning method for matching unsupervised data
US12561222B2 (en) * 2022-06-03 2026-02-24 Adobe Inc. Reducing bias in machine learning models utilizing a fairness deviation constraint and decision matrix
CN115048425B (zh) * 2022-06-09 2025-04-11 深圳计算科学研究院 一种基于强化学习的数据筛选方法及其装置
US20240020515A1 (en) * 2022-07-06 2024-01-18 University Of Southern California Systems and methods for a neural network database framework for answering database query types
CN118175048A (zh) * 2022-12-09 2024-06-11 维沃移动通信有限公司 模型监督触发方法、装置、ue、网络侧设备、可读存储介质及通信系统
US12475132B2 (en) 2023-02-20 2025-11-18 Capital One Financial Corporation Computing system and method for applying monte carlo estimation to determine the contribution of dependent input variable groups on the output of a data science model

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9008840B1 (en) 2013-04-19 2015-04-14 Brain Corporation Apparatus and methods for reinforcement-guided supervised learning
US20180012137A1 (en) 2015-11-24 2018-01-11 The Research Foundation for the State University New York Approximate value iteration with complex returns by bounding

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009237923A (ja) * 2008-03-27 2009-10-15 Nec Corp 学習方法およびシステム
US20180082185A1 (en) * 2015-03-23 2018-03-22 Nec Corporation Predictive model updating system, predictive model updating method, and predictive model updating program
US11144616B2 (en) * 2017-02-22 2021-10-12 Cisco Technology, Inc. Training distributed machine learning with selective data transfers
JP6917004B2 (ja) * 2017-04-20 2021-08-11 オムロン株式会社 評価装置、評価方法及びそのプログラム
US20180341851A1 (en) * 2017-05-24 2018-11-29 International Business Machines Corporation Tuning of a machine learning system
US11176487B2 (en) * 2017-09-28 2021-11-16 Oracle International Corporation Gradient-based auto-tuning for machine learning and deep learning models
CN108062587A (zh) * 2017-12-15 2018-05-22 清华大学 一种无监督机器学习的超参数自动优化方法及系统
CN109242105B (zh) * 2018-08-17 2024-03-15 第四范式（北京）技术有限公司 代码优化方法、装置、设备及介质

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9008840B1 (en) 2013-04-19 2015-04-14 Brain Corporation Apparatus and methods for reinforcement-guided supervised learning
US20180012137A1 (en) 2015-11-24 2018-01-11 The Research Foundation for the State University New York Approximate value iteration with complex returns by bounding

Also Published As

Publication number Publication date
WO2020208444A1 (en) 2020-10-15
CN113692594A (zh) 2021-11-23
GB2597406A (en) 2022-01-26
JP2022527536A (ja) 2022-06-02
US20200320428A1 (en) 2020-10-08

Similar Documents

Publication Publication Date Title
DE112020000537T5 (de) Verbesserung von fairness durch bestärkendes lernen
US20220180199A1 (en) Neural network model compression method and apparatus, storage medium, and chip
DE112020005610T5 (de) Identifizieren von optimalen gewichtungen zum verbessern einervorhersagegenauigkeit bei methoden für maschinelles lernen
DE112021006232T5 (de) Proaktive anomalieerkennung
DE112020000584T5 (de) Verfahren für unüberwachte bild-zu-bild-übersetzung mit wenigen aufnahmen
DE112018005227T5 (de) Merkmalsextraktion mithilfe von multi-task-lernen
DE112022002622T5 (de) Abschwächen gegnerischer angriffe zur gleichzeitigen vorhersage und optimierung von modellen
DE112023001690T5 (de) Erklärbare klassifizierungen mit verzicht unter verwendung von kundenagnostischen maschinellen lernmodellen
DE112020001034T5 (de) Seltene fälle berücksichtigende trainingsdaten für künstliche intelligenz
DE102020210352A1 (de) Verfahren und Vorrichtung zum Transferlernen zwischen modifizierten Aufgaben
DE112021002453T5 (de) Iteratives trainieren eines modells für maschinelles lernen
DE112020002684T5 (de) Ein Mehrfachverfahrenssystem für optimale Vorhersagemodellauswahl
DE112021004652T5 (de) Hintertürerkennung gegnerischer Interpolation
DE112017007492T5 (de) System und Verfahren zur Erfassung von Objekten in einem digitalen Bild und System und Verfahren zur Neubewertung von Objekterfassungen
DE112021004714T5 (de) Ordinale zeitreihenklassifizierung mit fehlender information
DE102024206000A1 (de) System und Verfahren für Suchen Nach Prompts
DE202019105282U1 (de) Vorrichtung zum Optimieren eines System für das maschinelle Lernen
DE102023210093A1 (de) System und Verfahren zum effizienten Analysieren und Vergleichen von Maschinenlernmodellen auf Slice-Basis
DE102020132591A1 (de) Auswählen von rechenkernvarianten unter verwendung neuronaler netzwerke
EP3557487A1 (de) Generieren von validierungsdaten mit generativen kontradiktorischen netzwerken
DE112021000251T5 (de) Verfahren zum auswählen von datensätzen zum aktualisieren eines moduls mit künstlicher intelligenz
EP4216110A1 (en) A quantization method to improve the fidelity of rule extraction algorithms for use with artificial neural networks
DE112022000465T5 (de) Automatisiertes einstufen von befehlsketten zur zeitreihenprognose
DE102024115705A1 (de) Entfernung von audioverzerrung basierend auf einer menge von referenzaudiosamples
DE102023210092A1 (de) System und Verfahren für einen Rahmen der visuellen Analytik für Maschinenlernmodelle auf Slice-Basis

Legal Events

Date Code Title Description
R012 Request for examination validly filed
R084 Declaration of willingness to licence
R119 Application deemed withdrawn, or ip right lapsed, due to non-payment of renewal fee