Proactive Message Passing on Memory Factor Networks
This work provides a new graphical model and algorithm for inference in structured data, but it appears incremental as it builds on existing message-passing techniques without addressing a specific high-impact bottleneck.
The paper tackles the problem of modeling structured data by introducing memory factor networks (MFNs) and a proactive message-passing (PMP) algorithm for inference, resulting in an efficient method with convergence guarantees compared to belief propagation variants.
We introduce a new type of graphical model that we call a "memory factor network" (MFN). We show how to use MFNs to model the structure inherent in many types of data sets. We also introduce an associated message-passing style algorithm called "proactive message passing"' (PMP) that performs inference on MFNs. PMP comes with convergence guarantees and is efficient in comparison to competing algorithms such as variants of belief propagation. We specialize MFNs and PMP to a number of distinct types of data (discrete, continuous, labelled) and inference problems (interpolation, hypothesis testing), provide examples, and discuss approaches for efficient implementation.