A Review on Machine Unlearning

Zhang, Haibo; Nakamura, Tôru; Isohara, Takamasa; Sakurai, Kouichi

doi:10.1007/s42979-023-01767-4

Cited by 9 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine unlearning is the process of effectively removing specific data or information from a model [11,12]. This concept is particularly important for privacy protection, data deletion requests (e.g., "right to be forgotten" (https://gdpr.eu/right-to-be-forgotten/ (accessed on 20 March 2024))), or simple outdated or incorrect information removal from the model.…”

Section: Machine Unlearningmentioning

confidence: 99%

“…The removal of unnecessary information from a trained model often involves removing data from the original dataset and retraining the model from scratch, which are timeconsuming and cost-intensive. Therefore, several approaches have been developed to efficiently remove specific information without retraining the model from scratch [11][12][13][14][15]. These methods segment certain parts of the model or change the learning process to reduce costs while maintaining the model accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Continual Learning Techniques for Image Generative Models with Learned Class Information Management

Togo,

Maeda

et al. 2024

Sensors

View full text Add to dashboard Cite

The advancements in deep learning have significantly enhanced the capability of image generation models to produce images aligned with human intentions. However, training and adapting these models to new data and tasks remain challenging because of their complexity and the risk of catastrophic forgetting. This study proposes a method for addressing these challenges involving the application of class-replacement techniques within a continual learning framework. This method utilizes selective amnesia (SA) to efficiently replace existing classes with new ones while retaining crucial information. This approach improves the model’s adaptability to evolving data environments while preventing the loss of past information. We conducted a detailed evaluation of class-replacement techniques, examining their impact on the “class incremental learning” performance of models and exploring their applicability in various scenarios. The experimental results demonstrated that our proposed method could enhance the learning efficiency and long-term performance of image generation models. This study broadens the application scope of image generation technology and supports the continual improvement and adaptability of corresponding models.

show abstract

Section: Machine Unlearningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Analysis of Continual Learning Techniques for Image Generative Models with Learned Class Information Management

Togo,

Maeda

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…making the models unlearn an example. There has been some work in developing unlearning techniques for models, but this is still an open problem in ML [75–77] with a need for effective and time‐saving solutions. AI in healthcare brings with it a number of ethical concerns, for instance, the potential to aggravate discrimination and inequality due to biased ML algorithms [78].…”

Section: Limitations Challenges and Recommendationsmentioning

confidence: 99%

Unleashing the potential of AI for pathology: challenges and recommendations

Asif

Rajpoot

Graham

et al. 2023

The Journal of Pathology

View full text Add to dashboard Cite

Computational pathology is currently witnessing a surge in the development of AI techniques, offering promise for achieving breakthroughs and significantly impacting the practices of pathology and oncology. These AI methods bring with them the potential to revolutionize diagnostic pipelines as well as treatment planning and overall patient care. Numerous peer‐reviewed studies reporting remarkable performance across diverse tasks serve as a testimony to the potential of AI in the field. However, widespread adoption of these methods in clinical and pre‐clinical settings still remains a challenge. In this review article, we present a detailed analysis of the major obstacles encountered during the development of effective models and their deployment in practice. We aim to provide readers with an overview of the latest developments, assist them with insights into identifying some specific challenges that may require resolution, and suggest recommendations and potential future research directions. © 2023 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

show abstract

“…To this end, another important aspect of community-driven AI moderation is unlearning [25], [26] i.e., excluding some training results after they have already been included in the model. Federated machine unlearning represents the collective process of detecting sensitive and inaccurate predictions in a community-driven AI model and collaboratively unlearning the information housed within the model.…”

Section: E Federated Machine Unlearningmentioning

confidence: 99%

Towards Community-Driven Generative AI

Dautov,

Husom,

Sen

et al. 2023

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

While the emerging market of Generative Artificial Intelligence (AI) is increasingly dominated and controlled by the Tech Giants, there is also a growing interest in open-source AI code and models from smaller companies, research organisations and individual users. They often have valuable data that could be used for training, but their computing resources are limited, while data privacy concerns prevent them from sharing this data for public training. A possible solution to overcome these two issues is to utilise the crowd-souring principles and apply federated learning techniques to build a distributed privacypreserving architecture for training Generative AI. This paper discusses how these two key enablers, together with some other emerging technologies, can be effectively combined to build a community-driven Generative AI ecosystem, allowing even small actors to participate in the training of Generative AI models by securely contributing their training data. The paper also discusses related non-technical issues, such as the role of the community and intellectual property rights, and outlines further research directions associated with AI moderation.

show abstract

A Review on Machine Unlearning

Cited by 9 publications

References 44 publications

Analysis of Continual Learning Techniques for Image Generative Models with Learned Class Information Management

Analysis of Continual Learning Techniques for Image Generative Models with Learned Class Information Management

Unleashing the potential of AI for pathology: challenges and recommendations

Towards Community-Driven Generative AI

Contact Info

Product

Resources

About