Related papers: Meta-Generalization for Multiparty Privacy Learnin…

Imitation learning holds the promise of equipping robots with versatile skills by learning from expert demonstrations. However, policies trained on finite datasets often struggle to generalize beyond the training distribution. In this work,…

This paper introduces PriMaL, a general PRIvacy-preserving MAchine-Learning method for reducing the privacy cost of information transmitted through a network. Distributed sensor networks are often used for automated classification and…

This paper investigates the problem of forecasting multivariate aggregated human mobility while preserving the privacy of the individuals concerned. Differential privacy, a state-of-the-art formal notion, has been used as the privacy…

Meta-learning models have two objectives. First, they need to be able to make predictions over a range of task distributions while utilizing only a small amount of training data. Second, they also need to adapt to new novel unseen tasks at…

Modern deep learning techniques focus on extracting intricate information from data to achieve accurate predictions. However, the training datasets may be crowdsourced and include sensitive information, such as personal contact details,…

Generalizing to out-of-distribution data while being aware of model fairness is a significant and challenging problem in meta-learning. The goal of this problem is to find a set of fairness-aware invariant parameters of classifier that is…

Collaborative training of neural networks leverages distributed data by exchanging gradient information between different clients. Although training data entirely resides with the clients, recent work shows that training data can be…

The goal of meta-learning is to train a model on a variety of learning tasks, such that it can adapt to new problems within only a few iterations. Here we propose a principled information-theoretic model that optimally partitions the…

Due to data privacy constraints, data sharing among multiple clinical centers is restricted, which impedes the development of high performance deep learning models from multicenter collaboration. Naive weight transfer methods share…

Consider two data providers, each maintaining private records of different feature sets about common entities. They aim to learn a linear model jointly in a federated setting, namely, data is local and a shared model is trained from locally…

Federated learning enables the deployment of machine learning to problems for which centralized data collection is impractical. Adding differential privacy guarantees bounds on privacy while data are contributed to a global model. Adding…

Differential privacy is the state-of-the-art definition for privacy, guaranteeing that any analysis performed on a sensitive dataset leaks no information about the individuals whose data are contained therein. In this thesis, we develop…

Federated learning with differential privacy, or private federated learning, provides a strategy to train machine learning models while respecting users' privacy. However, differential privacy can disproportionately degrade the performance…

Machine learning benefits from large training datasets, which may not always be possible to collect by any single entity, especially when using privacy-sensitive data. In many contexts, such as healthcare and finance, separate parties may…

As people's demand for personal privacy and data security becomes a priority, encrypted traffic has become mainstream in the cyber world. However, traffic encryption is also shielding malicious and illegal traffic introduced by adversaries,…

Graph Machine Learning (GraphML), whereby classical machine learning is generalized to irregular graph domains, has enjoyed a recent renaissance, leading to a dizzying array of models and their applications in several domains. With its…

Duplication is a prevalent issue within datasets. Existing research has demonstrated that the presence of duplicated data in training datasets can significantly influence both model performance and data privacy. However, the impact of data…

Balancing differential privacy (DP) with recommendation accuracy is a key challenge in privacy-preserving recommender systems, since DP-noise degrades accuracy. We address this trade-off at both the data and model levels. At the data level,…

Federated learning involves a central processor that works with multiple agents to find a global model. The process consists of repeatedly exchanging estimates, which results in the diffusion of information pertaining to the local private…

A central issue in machine learning is how to train models on sensitive user data. Industry has widely adopted a simple algorithm: Stochastic Gradient Descent with noise (a.k.a. Stochastic Gradient Langevin Dynamics). However, foundational…