arXiv research

Estimates population mean from user-level data with privacy, accounting for heterogeneity.

This paper analyzes user-level local differential privacy in distributed systems.

Novel mean estimation method under user-level differential privacy reduces noise in continual mean estimates.

Develops privacy-preserving methods for longitudinal linear regression.

Paper studies user-level differential privacy in federated linear contextual bandits.

New attack recovers user-level information from large batch images.

A new algorithm estimates mean under varying user data sizes with local differential privacy.

New algorithms protect user-level privacy in learning tasks.

New method uses Winsorized mean estimators for privacy-preserving statistics on dependent data.

Recommender systems often face heterogeneous datasets containing highly personalized historical data of users, where no single model could give the best recommendation for every user. We observe this ubiquitous phenomenon on both public and private datasets and address the model selection problem in pursuit of optimizi…

New privacy mechanism for user-level discrete distributions with reduced penalty.

CDA framework infers channel influence from aggregated data without user identifiers.

New algorithm optimizes privacy and utility in multi-task learning with skewed data.

Study shows FL reduces unintended memorization by clustering data and using strong user-level privacy.

Private ALS method improves matrix completion with tighter rates and better privacy.

Social Media has seen a tremendous growth in the last decade and is continuing to grow at a rapid pace. With such adoption, it is increasingly becoming a rich source of data for opinion mining and sentiment analysis. The detection and analysis of sentiment in social media is thus a valuable topic and attracts a lot of …

Improved locally private sparse estimation with multiple samples per user.

Model clusters authors and topics in short texts like social media posts.

This paper describes a practical system for Multi Touch Attribution (MTA) for use by a publisher of digital ads. We developed this system for JD.com, an eCommerce company, which is also a publisher of digital ads in China. The approach has two steps. The first step ('response modeling') fits a user-level model for purc…

Novel algorithm reduces privacy noise in machine learning.

We introduce the BriarPatch, a pixel-space intervention that obscures sensitive attributes from representations encoded in pre-trained classifiers. The patches encourage internal model representations not to encode sensitive information, which has the effect of pushing downstream predictors towards exhibiting demograph…

We summarize the potential impact that the European Union's new General Data Protection Regulation will have on the routine use of machine learning algorithms. Slated to take effect as law across the EU in 2018, it will restrict automated individual decision-making (that is, algorithms that make decisions based on user…

Paper improves privacy-accuracy balance in federated learning.

There is an increasing interest in exploiting mobile sensing technologies and machine learning techniques for mental health monitoring and intervention. Researchers have effectively used contextual information, such as mobility, communication and mobile phone usage patterns for quantifying individuals' mood and wellbei…

The evolution of social media users' behavior over time complicates user-level comparison tasks such as verification, classification, clustering, and ranking. As a result, naïve approaches may fail to generalize to new users or even to future observations of previously known users. In this paper, we propose a novel pro…

Structured subsampling improves privacy in deep time series forecasting.

Kolmogorov-Arnold network improves GW catalog posterior construction.

User engagement in online social networking depends critically on the level of social activity in the corresponding platform--the number of online actions, such as posts, shares or replies, taken by their users. Can we design data-driven algorithms to increase social activity? At a user level, such algorithms may incre…

Existing approaches for training neural networks with user-level differential privacy (e.g., DP Federated Averaging) in federated learning (FL) settings involve bounding the contribution of each user's model update by clipping it to some constant value. However there is no good a priori setting of the clipping norm acr…

Response time improves alignment with diverse human preferences.

Paper trains language models without memorizing user data.

Communication networks shared by many users are a widespread challenge nowadays. In this paper we address several aspects of this challenge simultaneously: learning unknown stochastic network characteristics, sharing resources with other users while keeping coordination overhead to a minimum. The proposed solution comb…

FedIRT enables privacy-preserving psychometric estimation without centralizing data.

Generative framework unifies and improves personalized learning and estimation methods.

Traffic prediction plays a vital role in efficient planning and usage of network resources in wireless networks. While traffic prediction in wired networks is an established field, there is a lack of research on the analysis of traffic in cellular networks, especially in a content-blind manner at the user level. Here, …

New DP mechanisms improve ML privacy-utility-computational tradeoffs.

Deep learning algorithms have recently produced state-of-the-art accuracy in many classification tasks, but this success is typically dependent on access to many annotated training examples. For domains without such data, an attractive alternative is to train models with light, or distant supervision. In this paper, we…

Much recent research aims to identify evidence for Drug-Drug Interactions (DDI) and Adverse Drug reactions (ADR) from the biomedical scientific literature. In addition to this "Bibliome", the universe of social media provides a very promising source of large-scale data that can help identify DDI and ADR in ways that ha…

A new method improves recommendation accuracy by learning from multiple networks and time-dependent user preferences.

Locally private online quantile regression method addresses privacy constraints.

Critical task and cognition-based environments, such as in military and defense operations, aviation user-technology interaction evaluation on UI, understanding intuitiveness of a hardware model or software toolkit, etc. require an assessment of how much a particular task is generating mental workload on a user. This i…

This paper improves privacy in federated learning without a trusted server.

Explainable recommendation is far from being well solved partly due to three challenges. The first is the personalization of preference learning, which requires that different items/users have different contributions to the learning of user preference or item quality. The second one is dynamic explanation, which is cru…

This paper shows how differential privacy can be achieved naturally in federated learning over fading channels without artificial noise.

We establish the first benchmark for federated learning with differential privacy in ASR, achieving competitive performance.

Big data sets must be carefully partitioned into statistically similar data subsets that can be used as representative samples for big data analysis tasks. In this paper, we propose the random sample partition (RSP) data model to represent a big data set as a set of non-overlapping data subsets, called RSP data blocks,…

Prevents sensitive data generation in diffusion models using labeled and unlabeled data.

Study reveals Data Shapley's inconsistent performance in data selection tasks.