Asynchronous Distributed Learning from Constraints

TL;DR

This paper extends Learning from Constraints to a distributed asynchronous setting, enabling multiple networked parties to collaboratively learn from shared and private constraints without central authority, with applications in digit recognition and document classification.

Contribution

It introduces a distributed asynchronous method for Learning from Constraints that preserves privacy and handles nonconvex constraints without a central coordinator.

Findings

Supports privacy-preserving distributed learning.

Applicable to nonconvex constraints in real-world tasks.

Demonstrated in digit recognition and document classification.

Abstract

In this paper, the extension of the framework of Learning from Constraints (LfC) to a distributed setting where multiple parties, connected over the network, contribute to the learning process is studied. LfC relies on the generic notion of "constraint" to inject knowledge into the learning problem and, due to its generality, it deals with possibly nonconvex constraints, enforced either in a hard or soft way. Motivated by recent progresses in the field of distributed and constrained nonconvex optimization, we apply the (distributed) Asynchronous Method of Multipliers (ASYMM) to LfC. The study shows that such a method allows us to support scenarios where selected constraints (i.e., knowledge), data, and outcomes of the learning process can be locally stored in each computational node without being shared with the rest of the network, opening the road to further investigations into privacy-preserving LfC. Constraints act as a bridge between what is shared over the net and what is private to each node and no central authority is required. We demonstrate the applicability of these ideas in two distributed real-world settings in the context of digit recognition and document classification.