Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models
Jul 12, 2020
Speakers
Amrita Roy Chowdhury
Speaker · 0 followers
Theodoros Rekatsinas
Speaker · 0 followers
Somesh Jha
Speaker · 1 follower
About
Directed graphical models (DGMs) are a class of probabilistic models that are widely used for predictive analysis in sensitive domains such as medical diagnostics. In this paper, we present an algorithm for differentially-private learning of the parameters of a DGM. Our solution optimizes for the utility of inference queries over the DGM and adds noise that is customized to the properties of the private input dataset and the graph structure of the DGM. To the best of our knowledge, this is the first explicit data-dependent privacy budget allocation algorithm in the context of DGMs. We compare our algorithm with a standard data-independent approach over a diverse suite of benchmarks and demonstrate that our solution requires a privacy budget that is roughly 3× smaller to obtain the same or higher utility.Directed graphical models (DGMs) are a class of probabilistic models that are widely used for predictive analysis in sensitive domains such as medical diagnostics. In this paper, we present an algorithm for differentially-private learning of the parameters of a DGM. Our solution optimizes for the utility of inference queries over the DGM and adds noise that is customized to the properties of the private input dataset and the graph structure of the DGM. To the best of our knowledge, this is the f…
Categories
Mathematics
Category · 2.4k presentations
AI & Data Science
Category · 10.8k presentations
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Incentivizing and Rewarding High-Quality Data via Influence Functions
Watch later
Analytic Marching: An Analytic Meshing Solution from Deep Implicit Surface Networks
Watch later
Jiabao Lei, …
Learning Affordances in Object-Centric Generative Models
Watch later
Inductive Relation Prediction by Subgraph Reasoning
Watch later
Introduction to Workshop on Continual Learning
Watch later
Robust Graph Representation Learning via Neural Sparsification
Watch later
Cheng Zheng, …