Scaling shared model governance via model splitting

by   Miljan Martic, et al.

Currently the only techniques for sharing governance of a deep learning model are homomorphic encryption and secure multiparty computation. Unfortunately, neither of these techniques is applicable to the training of large neural networks due to their large computational and communication overheads. As a scalable technique for shared model governance, we propose splitting deep learning model between multiple parties. This paper empirically investigates the security guarantee of this technique, which is introduced as the problem of model completion: Given the entire training data set or an environment simulator, and a subset of the parameters of a trained deep learning model, how much training is required to recover the model's original performance? We define a metric for evaluating the hardness of the model completion problem and study it empirically in both supervised learning on ImageNet and reinforcement learning on Atari and DeepMind Lab. Our experiments show that (1) the model completion problem is harder in reinforcement learning than in supervised learning because of the unavailability of the trained agent's trajectories, and (2) its hardness depends not primarily on the number of parameters of the missing part, but more so on their type and location. Our results suggest that model splitting might be a feasible technique for shared model governance in some settings where training is very expensive.



There are no comments yet.


page 7


Listwise Learning to Rank with Deep Q-Networks

Learning to Rank is the problem involved with ranking a sequence of docu...

Secure Data Sharing With Flow Model

In the classical multi-party computation setting, multiple parties joint...

Autonomous Driving in Reality with Reinforcement Learning and Image Translation

Supervised learning is widely used in training autonomous driving vehicl...

Compression and Localization in Reinforcement Learning for ATARI Games

Deep neural networks have become commonplace in the domain of reinforcem...

Finding the best design parameters for optical nanostructures using reinforcement learning

Recently, a novel machine learning model has emerged in the field of rei...

An Empirical Model of Large-Batch Training

In an increasing number of domains it has been demonstrated that deep le...

Fair Sharing: The Shapley Value for Ride-Sharing and Routing Games

Ride-sharing services are gaining popularity and are crucial for a susta...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.