Asynchronous Distributed Learning from Constraints
This work addresses privacy-preserving distributed learning for scenarios where multiple parties collaborate without a central authority, though it is incremental as it adapts existing optimization methods to LfC.
The paper tackles the problem of extending Learning from Constraints (LfC) to a distributed setting by applying the Asynchronous Method of Multipliers (ASYMM), enabling local storage of constraints, data, and outcomes without sharing across nodes, as demonstrated in digit recognition and document classification tasks.
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.