paper-with-me

Papers

Privacy in Metalearning and Multitask Learning: Modeling and Separations

2024-12-16 · Maryam Aliakbarpour, Konstantina Bairaktari, Adam Smith, Marika Swanberg, Jonathan Ullman

Model personalization allows a set of individuals, each facing a different learning task, to train models that are more accurate for each person than those they could develop individually. The goals of personalization are captured in a variety of formal frameworks, such as multitask learning and metalearning. Combining data for model personalization poses risks for privacy because the output of an individual's model can depend on the data of other individuals. In this work we undertake a systematic study of differentially private personalized learning. Our first main contribution is to construct a taxonomy of formal frameworks for private personalized learning. This taxonomy captures different formal frameworks for learning as well as different threat models for the attacker. Our second main contribution is to prove separations between the personalized learning problems corresponding to different choices. In particular, we prove a novel separation between private multitask learning and private metalearning.

📄 PDF Abstract BibTeX arXiv:2412.12374

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Metalearning with Very Few Samples Per Task

2023-12-21 · Maryam Aliakbarpour, Konstantina Bairaktari, Gavin Brown, Adam Smith 외

Metalearning and multitask learning are two frameworks for solving a group of related learning tasks more efficiently than we could hope to solve each of the individual tasks on their own. In multitask learning, we are g…

Binary Classification

Zero-shot Text Classification With Generative Language Models

2019-12-10 · Raul Puri, Bryan Catanzaro

This work investigates the use of natural language to enable zero-shot model adaptation to new tasks. We use text and metadata from social commenting platforms as a source for a simple pretraining task. We then provide t…

ClassificationGeneral ClassificationLanguage ModelingLanguage Modelling+3

MRP-LLM: Multitask Reflective Large Language Models for Privacy-Preserving Next POI Recommendation

2024-12-03 · Ziqing Wu, Zhu Sun, Dongxia Wang, Lu Zhang 외

Large language models (LLMs) have shown promising potential for next Point-of-Interest (POI) recommendation. However, existing methods only perform direct zero-shot prompting, leading to ineffective extraction of user pr…

Language ModelingLanguage ModellingLarge Language ModelPrivacy Preserving

Metalearning for Feature Selection

2017-03-20 · Ben Goertzel, Nil Geisweiller, Chris Poulin

A general formulation of optimization problems in which various candidate solutions may use different feature-sets is presented, encompassing supervised classification, automated program learning and other cases. A novel…

Classificationfeature selectionGeneral Classificationtext-classification+1

A Metalearning Approach for Physics-Informed Neural Networks (PINNs): Application to Parameterized PDEs

2021-10-26 · Michael Penwarden, Shandian Zhe, Akil Narayan, Robert M. Kirby

Physics-informed neural networks (PINNs) as a means of discretizing partial differential equations (PDEs) are garnering much attention in the Computational Science and Engineering (CS&E) world. At least two challenges ex…

BIG-bench Machine LearningPhysics-informed machine learningTransfer Learning