Multi-Entity Dependence Learning with Rich Context via Conditional Variational Auto-encoder

TL;DR

This paper introduces MEDL_CVAE, a deep learning framework that models complex dependencies among multiple entities using a conditional variational auto-encoder, effectively capturing rich contextual correlations in large-scale real-world datasets.

Contribution

The paper presents MEDL_CVAE, a novel end-to-end deep learning method that encodes multivariate conditional distributions, improving scalability and performance over previous approaches.

Findings

MEDL_CVAE effectively captures complex dependency structures.

It scales better than previous methods on large datasets.

It improves joint likelihood in real-world applications.

Abstract

Multi-Entity Dependence Learning (MEDL) explores conditional correlations among multiple entities. The availability of rich contextual information requires a nimble learning scheme that tightly integrates with deep neural networks and has the ability to capture correlation structures among exponentially many outcomes. We propose MEDL_CVAE, which encodes a conditional multivariate distribution as a generating process. As a result, the variational lower bound of the joint likelihood can be optimized via a conditional variational auto-encoder and trained end-to-end on GPUs. Our MEDL_CVAE was motivated by two real-world applications in computational sustainability: one studies the spatial correlation among multiple bird species using the eBird data and the other models multi-dimensional landscape composition and human footprint in the Amazon rainforest with satellite images. We show that MEDL_CVAE captures rich dependency structures, scales better than previous methods, and further improves on the joint likelihood taking advantage of very large datasets that are beyond the capacity of previous methods.