# SpaMHMM: Sparse Mixture of Hidden Markov Models for Graph Connected Entities

## TL;DR

This paper introduces SpaMHMM, a novel framework that models sequential data from graph-connected entities using a sparse mixture of shared hidden Markov models, leveraging graph topology for improved modeling.

## Contribution

The paper presents a new sparse mixture of hidden Markov models that jointly trains shared HMMs considering graph structure, enhancing modeling of connected entities' sequential data.

## Key findings

- Effective in multiple application domains
- Exploits graph topology for better modeling
- Produces sparse mixture models

## Abstract

We propose a framework to model the distribution of sequential data coming from a set of entities connected in a graph with a known topology. The method is based on a mixture of shared hidden Markov models (HMMs), which are jointly trained in order to exploit the knowledge of the graph structure and in such a way that the obtained mixtures tend to be sparse. Experiments in different application domains demonstrate the effectiveness and versatility of the method.