Multi-Entity Dependence Learning with Rich Context via Conditional Variational Auto-encoder
This work addresses the challenge of modeling multi-entity dependencies in large-scale datasets for domains like ecology and environmental monitoring, representing an incremental improvement over existing methods.
The paper tackles the problem of learning conditional correlations among multiple entities with rich contextual information by proposing MEDL_CVAE, a method based on conditional variational auto-encoders that optimizes the joint likelihood end-to-end. It shows that MEDL_CVAE captures rich dependency structures, scales better than previous methods, and improves joint likelihood on large datasets, with applications in computational sustainability using eBird and satellite data.
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.