MPLP: Learning a Message Passing Learning Protocol
This proposes a new learning paradigm for neural networks, potentially impacting deep learning fields, but it is incremental as it builds on existing meta-learning and message-passing concepts.
The paper tackles the problem of learning neural network weights by introducing a Message Passing Learning Protocol (MPLP), which abstracts operations as agents that pass messages, and demonstrates its viability on simple feed-forward networks as an alternative to gradient-based methods.
We present a novel method for learning the weights of an artificial neural network - a Message Passing Learning Protocol (MPLP). In MPLP, we abstract every operations occurring in ANNs as independent agents. Each agent is responsible for ingesting incoming multidimensional messages from other agents, updating its internal state, and generating multidimensional messages to be passed on to neighbouring agents. We demonstrate the viability of MPLP as opposed to traditional gradient-based approaches on simple feed-forward neural networks, and present a framework capable of generalizing to non-traditional neural network architectures. MPLP is meta learned using end-to-end gradient-based meta-optimisation. We further discuss the observed properties of MPLP and hypothesize its applicability on various fields of deep learning.