Fairness-Driven Private Collaborative Machine Learning

• URL: http://arxiv.org/abs/2109.14376v1
• Date: Wed, 29 Sep 2021 12:22:00 GMT
• Title: Fairness-Driven Private Collaborative Machine Learning
• Authors: Dana Pessach, Tamir Tassa, Erez Shmueli
• Abstract summary: We suggest a feasible privacy-preserving pre-process mechanism for enhancing fairness of collaborative machine learning algorithms. Our experimentation with the proposed method shows that it is able to enhance fairness considerably with only a minor compromise in accuracy.
• Score: 7.25130576615102
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The performance of machine learning algorithms can be considerably improved when trained over larger datasets. In many domains, such as medicine and finance, larger datasets can be obtained if several parties, each having access to limited amounts of data, collaborate and share their data. However, such data sharing introduces significant privacy challenges. While multiple recent studies have investigated methods for private collaborative machine learning, the fairness of such collaborative algorithms was overlooked. In this work we suggest a feasible privacy-preserving pre-process mechanism for enhancing fairness of collaborative machine learning algorithms. Our experimentation with the proposed method shows that it is able to enhance fairness considerably with only a minor compromise in accuracy.

Related papers

• Privacy-Preserving Graph Machine Learning from Data to Computation: A Survey [67.7834898542701]
  We focus on reviewing privacy-preserving techniques of graph machine learning. We first review methods for generating privacy-preserving graph data. Then we describe methods for transmitting privacy-preserved information.
  arXiv  Detail & Related papers  (2023-07-10T04:30:23Z)
• PILLAR: How to make semi-private learning more effective [12.292092677396347]
  In Semi-Supervised Semi-Private (SP) learning, the learner has access to both public unlabelled and private labelled data. We propose a computationally efficient algorithm that achieves significantly lower private labelled sample complexity and can be efficiently run on real-world datasets.
  arXiv  Detail & Related papers  (2023-06-06T18:45:05Z)
• Achieving Transparency in Distributed Machine Learning with Explainable Data Collaboration [5.994347858883343]
  A parallel trend has been to train machine learning models in collaboration with other data holders without accessing their data. This paper presents an Explainable Data Collaboration Framework based on a model-agnostic additive feature attribution algorithm.
  arXiv  Detail & Related papers  (2022-12-06T23:53:41Z)
• Decentralized Learning with Multi-Headed Distillation [12.90857834791378]
  Decentralized learning with private data is a central problem in machine learning. We propose a novel distillation-based decentralized learning technique that allows multiple agents with private non-iid data to learn from each other.
  arXiv  Detail & Related papers  (2022-11-28T21:01:43Z)
• Privacy-Preserving Machine Learning for Collaborative Data Sharing via Auto-encoder Latent Space Embeddings [57.45332961252628]
  Privacy-preserving machine learning in data-sharing processes is an ever-critical task. This paper presents an innovative framework that uses Representation Learning via autoencoders to generate privacy-preserving embedded data.
  arXiv  Detail & Related papers  (2022-11-10T17:36:58Z)
• Asynchronous Collaborative Learning Across Data Silos [9.094748832034746]
  We propose a framework to enable asynchronous collaborative training of machine learning models across data silos. This allows data science teams to collaboratively train a machine learning model, without sharing data with one another.
  arXiv  Detail & Related papers  (2022-03-23T18:00:19Z)
• Non-IID data and Continual Learning processes in Federated Learning: A long road ahead [58.720142291102135]
  Federated Learning is a novel framework that allows multiple devices or institutions to train a machine learning model collaboratively while preserving their data private. In this work, we formally classify data statistical heterogeneity and review the most remarkable learning strategies that are able to face it. At the same time, we introduce approaches from other machine learning frameworks, such as Continual Learning, that also deal with data heterogeneity and could be easily adapted to the Federated Learning settings.
  arXiv  Detail & Related papers  (2021-11-26T09:57:11Z)
• Can Active Learning Preemptively Mitigate Fairness Issues? [66.84854430781097]
  dataset bias is one of the prevailing causes of unfairness in machine learning. We study whether models trained with uncertainty-based ALs are fairer in their decisions with respect to a protected class. We also explore the interaction of algorithmic fairness methods such as gradient reversal (GRAD) and BALD.
  arXiv  Detail & Related papers  (2021-04-14T14:20:22Z)
• Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data [77.88594632644347]
  Decentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks. In realistic learning scenarios, the presence of heterogeneity across different clients' local datasets poses an optimization challenge. We propose a novel momentum-based method to mitigate this decentralized training difficulty.
  arXiv  Detail & Related papers  (2021-02-09T11:27:14Z)
• Additively Homomorphical Encryption based Deep Neural Network for Asymmetrically Collaborative Machine Learning [12.689643742151516]
  preserving machine learning creates a constraint which limits further applications in finance sectors. We propose a new practical scheme of collaborative machine learning that one party owns data, but another party owns labels only. Our experiments on different datasets demonstrate not only stable training without accuracy, but also more than 100 times speedup.
  arXiv  Detail & Related papers  (2020-07-14T06:43:25Z)
• User-Level Privacy-Preserving Federated Learning: Analysis and Performance Optimization [77.43075255745389]
  Federated learning (FL) is capable of preserving private data from mobile terminals (MTs) while training the data into useful models. From a viewpoint of information theory, it is still possible for a curious server to infer private information from the shared models uploaded by MTs. We propose a user-level differential privacy (UDP) algorithm by adding artificial noise to the shared models before uploading them to servers.
  arXiv  Detail & Related papers  (2020-02-29T10:13:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.