Conventional federated learning directly averages model weights, which is only possible for
collaboration between models with homogeneous architectures. Sharing prediction instead …

This paper presents an active distillation method for a local institution (eg, hospital) to find
the best queries within its given budget to distill an on-server black-box model's predictive …

Federated Learning for Privacy-preserving data access Page 1 1 Federated Learning for
Privacy-preserving data access Malgorzata Smietanka1, 2, Hirsh Pithadia1,3, Philip Treleaven1 …

Federated learning suffers in the case of non-iid local datasets, ie, when the distributions of
the clients' data are heterogeneous. One promising approach to this challenge is the …

Federal tax data, derived from individuals' and businesses' tax and information returns, are
invaluable resources for research on a range of topics. That research improves our …

Federated learning and privacy Page 1 90 COMMUNICATIONS OF THE ACM | APRIL 2022 |
VOL. 65 | NO. 4 practice DOI:10.1145/3500240 Article development led by queue.acm.org …

Smart Meters (SMs) are IoT end devices used to collect user utility consumption withlimited
processing power on the edge of the smart grid (SG). While SMs have …

Abstract Latent Dirichlet Allocation (LDA) is a widely adopted topic model for industrial-
grade text mining applications. However, its performance heavily relies on the collection of …

Differentially private data releases are often required to satisfy a set of external constraints
that reflect the legal, ethical, and logical mandates to which the data curator is obligated. The …