JP2024520312A - 人工知能モジュール訓練中のバイアス低減 - Google Patents

人工知能モジュール訓練中のバイアス低減 Download PDF

Info

Publication number
JP2024520312A
JP2024520312A JP2023570346A JP2023570346A JP2024520312A JP 2024520312 A JP2024520312 A JP 2024520312A JP 2023570346 A JP2023570346 A JP 2023570346A JP 2023570346 A JP2023570346 A JP 2023570346A JP 2024520312 A JP2024520312 A JP 2024520312A
Authority
JP
Japan
Prior art keywords
artificial intelligence
metric
fairness
training
analysis results
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
JP2023570346A
Other languages
English (en)
Japanese (ja)
Other versions
JP2024520312A5 (enExample
Inventor
クミエロウスキ、ルーカス
クハルチク、シモン
ヒルツェル、マーティン
ラジャク、ドロタ
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 JP2024520312A publication Critical patent/JP2024520312A/ja
Publication of JP2024520312A5 publication Critical patent/JP2024520312A5/ja
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • 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
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • 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
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • 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
    • G06N3/047—Probabilistic or stochastic networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • 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)
  • 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)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Complex Calculations (AREA)
JP2023570346A 2021-06-07 2022-06-01 人工知能モジュール訓練中のバイアス低減 Pending JP2024520312A (ja)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US17/303,732 2021-06-07
US17/303,732 US20220391683A1 (en) 2021-06-07 2021-06-07 Bias reduction during artifical intelligence module training
PCT/IB2022/055104 WO2022259089A1 (en) 2021-06-07 2022-06-01 Bias reduction during artifical intelligence module training

Publications (2)

Publication Number Publication Date
JP2024520312A true JP2024520312A (ja) 2024-05-24
JP2024520312A5 JP2024520312A5 (enExample) 2024-07-31

Family

ID=84284694

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2023570346A Pending JP2024520312A (ja) 2021-06-07 2022-06-01 人工知能モジュール訓練中のバイアス低減

Country Status (3)

Country Link
US (1) US20220391683A1 (enExample)
JP (1) JP2024520312A (enExample)
WO (1) WO2022259089A1 (enExample)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12614109B1 (en) * 2021-10-12 2026-04-28 Virtuous AI, Inc. AI platform with automatic analysis data and methods for use therewith
US20240070744A1 (en) * 2022-08-19 2024-02-29 Salesforce, Inc. Systems and methods for self-guided sequence selection and extrapolation
US12487890B2 (en) * 2023-11-16 2025-12-02 Salesforce, Inc. Automated data backup

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200302524A1 (en) * 2019-03-18 2020-09-24 Zestfinance, Inc. Systems and methods for model fairness

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10360517B2 (en) * 2017-02-22 2019-07-23 Sas Institute Inc. Distributed hyperparameter tuning system for machine learning
US11431582B2 (en) * 2018-05-05 2022-08-30 Fmr Llc Systems and methods for context aware adaptation of services and resources in a distributed computing system
WO2020146028A1 (en) * 2019-01-07 2020-07-16 Google Llc Identifying and correcting label bias in machine learning
US20200226489A1 (en) * 2019-01-14 2020-07-16 Adobe Inc. Facilitating online resource access with bias corrected training data generated for fairness-aware predictive models
US20200320428A1 (en) * 2019-04-08 2020-10-08 International Business Machines Corporation Fairness improvement through reinforcement learning
US11416743B2 (en) * 2019-04-25 2022-08-16 International Business Machines Corporation Swarm fair deep reinforcement learning
US11775863B2 (en) * 2019-05-22 2023-10-03 Oracle International Corporation Enforcing fairness on unlabeled data to improve modeling performance
CN110782004B (zh) * 2019-09-26 2022-06-21 超参数科技(深圳)有限公司 模型训练方法、模型调用方法、设备及可读存储介质
US11443236B2 (en) * 2019-11-22 2022-09-13 International Business Machines Corporation Enhancing fairness in transfer learning for machine learning models with missing protected attributes in source or target domains
US12423574B2 (en) * 2020-02-18 2025-09-23 Royal Bank Of Canada System and method for weather dependent machine learning architecture
US20210295170A1 (en) * 2020-03-17 2021-09-23 Microsoft Technology Licensing, Llc Removal of engagement bias in online service
CN112541579B (zh) * 2020-12-23 2023-08-08 北京北明数科信息技术有限公司 模型训练方法、贫困程度信息识别方法、装置和存储介质
US12443676B2 (en) * 2021-10-13 2025-10-14 International Business Machines Corporation Controlling a bias of a machine learning module background

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200302524A1 (en) * 2019-03-18 2020-09-24 Zestfinance, Inc. Systems and methods for model fairness

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
CHEREPANOVA VALERIIA ET AL.: "Technical Challenges for Training Fair Neural Networks", ARXIV.ORG［ONLINE］, vol. arXiv:2102.06764v1, JPN6025040192, 12 February 2021 (2021-02-12), ISSN: 0005705950 *
神嶌 敏弘: "公平ロジスティック回帰での確定的決定則の影響", 人工知能学会 第32回全国大会論文集, vol. 2P3-03, JPN6025040193, 6 July 2018 (2018-07-06), pages 1 - 4, ISSN: 0005705949 *
金城 敬太: "多目的最適化を利用した公平性な機械学習", 人工知能学会 知識ベースシステム研究会資料, vol. SIG-KBS-C001-02, JPN6025040194, 21 August 2020 (2020-08-21), JP, pages 5 - 10, ISSN: 0005705948 *

Also Published As

Publication number Publication date
WO2022259089A1 (en) 2022-12-15
US20220391683A1 (en) 2022-12-08

Similar Documents

Publication Publication Date Title
US12014282B2 (en) Data processing method and apparatus, electronic device, and storage medium
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
US11004012B2 (en) Assessment of machine learning performance with limited test data
JP2024520312A (ja) 人工知能モジュール訓練中のバイアス低減
US9405427B2 (en) Adaptive user interface using machine learning model
US12309173B2 (en) Performance monitoring in the anomaly detection domain for the IT environment
US9916395B2 (en) Determining answer stability in a question answering system
JP2023518220A (ja) 多様なテキストを自動的に生成する方法
US9542381B2 (en) Automatic training of a syntactic and semantic parser using a genetic algorithm
US11836219B2 (en) Training sample set generation from imbalanced data in view of user goals
US20190286698A1 (en) Dialog flow evaluation
US11036941B2 (en) Generating a plurality of document plans to generate questions from source text
US12182711B2 (en) Generation of neural network containing middle layer background
JP2022541444A (ja) 機械支援型エージェントにおける自然言語応答
US20230064961A1 (en) Query response relevance determination
US11663518B2 (en) Cognitive system virtual corpus training and utilization
US11971796B2 (en) Goal seek analysis based on status models
CN113568820A (zh) 监控模型的方法、装置、电子设备和介质
CN111950580A (zh) 使用平衡训练集的分类器的预测准确性
CN107766577A (zh) 一种舆情监测方法、装置、设备及存储介质
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）
US9235808B2 (en) Evaluation of predictions in the absence of a known ground truth
US11586520B2 (en) Automated data linkages across datasets
WO2023160406A1 (en) Neural network inference quantization
JP7692966B2 (ja) 情報提供装置、情報提供方法、及び情報提供プログラム

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20240723

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20241114

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20250922

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20251009

A02 Decision of refusal

Free format text: JAPANESE INTERMEDIATE CODE: A02

Effective date: 20260331