JP2023058454A - 機械学習モジュールのバックグラウンドのバイアスの制御のためのコンピュータ実装方法、コンピュータプログラム製品およびコンピュータシステム（機械学習モジュールのバックグラウンドのバイアスの制御） - Google Patents

機械学習モジュールのバックグラウンドのバイアスの制御のためのコンピュータ実装方法、コンピュータプログラム製品およびコンピュータシステム（機械学習モジュールのバックグラウンドのバイアスの制御） Download PDF

Info

Publication number
JP2023058454A
JP2023058454A JP2022163230A JP2022163230A JP2023058454A JP 2023058454 A JP2023058454 A JP 2023058454A JP 2022163230 A JP2022163230 A JP 2022163230A JP 2022163230 A JP2022163230 A JP 2022163230A JP 2023058454 A JP2023058454 A JP 2023058454A
Authority
JP
Japan
Prior art keywords
module
data set
bias
feature
values
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
JP2022163230A
Other languages
English (en)
Japanese (ja)
Other versions
JP2023058454A5 (https=
Inventor
チミエロフスキ、ジー、ルカシュ
G Cmielowski Lukasz
クチャルチク、シモン
Kucharczyk Szymon
ラクザック、ドロタ
Laczak Dorota
リシュカ、ヤクブ、ダニエル
Jakub Ryszka Daniel
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 JP2023058454A publication Critical patent/JP2023058454A/ja
Publication of JP2023058454A5 publication Critical patent/JP2023058454A5/ja
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/211—Selection of the most significant subset of features
    • G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/211—Selection of the most significant subset of features
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
    • G06F18/2193—Validation; Performance evaluation; Active pattern learning techniques based on specific statistical tests
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/40—Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Medical Informatics (AREA)
  • Human Computer Interaction (AREA)
  • Probability & Statistics with Applications (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Complex Calculations (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
JP2022163230A 2021-10-13 2022-10-11 機械学習モジュールのバックグラウンドのバイアスの制御のためのコンピュータ実装方法、コンピュータプログラム製品およびコンピュータシステム（機械学習モジュールのバックグラウンドのバイアスの制御） Pending JP2023058454A (ja)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US17/450,694 2021-10-13
US17/450,694 US12443676B2 (en) 2021-10-13 2021-10-13 Controlling a bias of a machine learning module background

Publications (2)

Publication Number Publication Date
JP2023058454A true JP2023058454A (ja) 2023-04-25
JP2023058454A5 JP2023058454A5 (https=) 2026-01-19

Family

ID=85797029

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2022163230A Pending JP2023058454A (ja) 2021-10-13 2022-10-11 機械学習モジュールのバックグラウンドのバイアスの制御のためのコンピュータ実装方法、コンピュータプログラム製品およびコンピュータシステム（機械学習モジュールのバックグラウンドのバイアスの制御）

Country Status (2)

Country Link
US (1) US12443676B2 (https=)
JP (1) JP2023058454A (https=)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220391683A1 (en) * 2021-06-07 2022-12-08 International Business Machines Corporation Bias reduction during artifical intelligence module training
US12481919B2 (en) * 2022-04-25 2025-11-25 Business Objects Software Ltd. Discrimination likelihood estimate for trained machine learning model

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107430610A (zh) * 2015-02-13 2017-12-01 澳大利亚国家Ict有限公司 从分布式数据学习

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020164070A1 (en) * 2001-03-14 2002-11-07 Kuhner Mark B. Automatic algorithm generation
US20200372304A1 (en) 2018-07-31 2020-11-26 Microsoft Technology Licensing, Llc Quantifying bias in machine learning models
CA3134043C (en) 2019-03-18 2024-10-29 Zestfinance, Inc. MODEL EQUITY SYSTEMS AND METHODS
US20200320428A1 (en) 2019-04-08 2020-10-08 International Business Machines Corporation Fairness improvement through reinforcement learning
US11775863B2 (en) 2019-05-22 2023-10-03 Oracle International Corporation Enforcing fairness on unlabeled data to improve modeling performance

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107430610A (zh) * 2015-02-13 2017-12-01 澳大利亚国家Ict有限公司 从分布式数据学习
JP2018511109A (ja) * 2015-02-13 2018-04-19 ナショナル・アイシーティ・オーストラリア・リミテッド 分散データからの学習

Also Published As

Publication number Publication date
US20230115067A1 (en) 2023-04-13
US12443676B2 (en) 2025-10-14

Similar Documents

Publication Publication Date Title
US11636185B2 (en) AI governance using tamper proof model metrics
US20200320428A1 (en) Fairness improvement through reinforcement learning
CN110532376B (zh) 分类文本以确定用于选择机器学习算法结果的目标类型
US11741371B2 (en) Automatically generating diverse text
US11853877B2 (en) Training transfer-focused models for deep learning
US12008484B2 (en) Aggregated feature importance for finding influential business metrics
CN113826125A (zh) 使用无监督数据增强来训练机器学习模型
US20220114401A1 (en) Predicting performance of machine learning models
US11281999B2 (en) Predictive accuracy of classifiers using balanced training sets
US20220114473A1 (en) Predictive Data and Model Selection for Transfer Learning in Natural Language Processing
US20210150335A1 (en) Predictive model performance evaluation
JP2023058454A (ja) 機械学習モジュールのバックグラウンドのバイアスの制御のためのコンピュータ実装方法、コンピュータプログラム製品およびコンピュータシステム（機械学習モジュールのバックグラウンドのバイアスの制御）
US12505350B2 (en) Adaptive self-adversarial negative sampling for graph neural network training
JP2023520313A (ja) 不確定区間を有する性能予測の生成
JP2024504179A (ja) 人工知能推論モデルを軽量化する方法およびシステム
CN108604313B (zh) 自动化的预测性建模与框架
US20230236829A1 (en) Monolithic computer application refactoring
CN113469204A (zh) 数据处理方法、装置、设备和计算机存储介质
US11774498B2 (en) Multi-rate sampling for hierarchical system analysis
US20240232686A1 (en) Portion-Specific Model Compression for Optimization of Machine-Learned Models
JP2023035911A (ja) 人工知能モデルを訓練する方法、コンピュータシステム、コンピュータプログラム（管理限界を使用して人工知能モデル訓練を早期停止すること）
US20230206114A1 (en) Fair selective classification via a variational mutual information upper bound for imposing sufficiency
WO2025101527A1 (en) Techniques for learning co-engagement and semantic relationships using graph neural networks
US12341913B2 (en) Systems and methods for generating authentication quizzes
US12547938B2 (en) Correlation-based dimensional reduction of synthesized features

Legal Events

Date Code Title Description
RD16 Notification of change of power of sub attorney

Free format text: JAPANESE INTERMEDIATE CODE: A7436

Effective date: 20221222

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20250313

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20260108

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20260120

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20260127

A524 Written submission of copy of amendment under article 19 pct

Free format text: JAPANESE INTERMEDIATE CODE: A524

Effective date: 20260402

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20260416