Federated Reconnaissance: Efficient, Distributed, Class-Incremental Learning
We describe federated reconnaissance, a class of learning problems in which distributed clients learn new concepts independently and communicate that knowledge efficiently. In particular, we propose an evaluation framework and methodological baseline for a system in which each client is expected to...
Saved in:
Main Authors | , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
31.08.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | We describe federated reconnaissance, a class of learning problems in which
distributed clients learn new concepts independently and communicate that
knowledge efficiently. In particular, we propose an evaluation framework and
methodological baseline for a system in which each client is expected to learn
a growing set of classes and communicate knowledge of those classes efficiently
with other clients, such that, after knowledge merging, the clients should be
able to accurately discriminate between classes in the superset of classes
observed by the set of clients. We compare a range of learning algorithms for
this problem and find that prototypical networks are a strong approach in that
they are robust to catastrophic forgetting while incorporating new information
efficiently. Furthermore, we show that the online averaging of prototype
vectors is effective for client model merging and requires only a small amount
of communication overhead, memory, and update time per class with no
gradient-based learning or hyperparameter tuning. Additionally, to put our
results in context, we find that a simple, prototypical network with four
convolutional layers significantly outperforms complex, state of the art
continual learning algorithms, increasing the accuracy by over 22% after
learning 600 Omniglot classes and over 33% after learning 20 mini-ImageNet
classes incrementally. These results have important implications for federated
reconnaissance and continual learning more generally by demonstrating that
communicating feature vectors is an efficient, robust, and effective means for
distributed, continual learning. |
---|---|
DOI: | 10.48550/arxiv.2109.00150 |