Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs
This work addresses the problem of computational inefficiency in generative models for tree-structured data, which is incremental as it builds on existing probabilistic circuits.
The paper tackled the challenge of tractable probabilistic inference for tree-structured graphs, such as XML and JSON, by proposing sum-product-set networks, which extend probabilistic circuits to handle variable graph structures with exact and efficient inference, achieving performance comparable to intractable neural network models.
Daily internet communication relies heavily on tree-structured graphs, embodied by popular data formats such as XML and JSON. However, many recent generative (probabilistic) models utilize neural networks to learn a probability distribution over undirected cyclic graphs. This assumption of a generic graph structure brings various computational challenges, and, more importantly, the presence of non-linearities in neural networks does not permit tractable probabilistic inference. We address these problems by proposing sum-product-set networks, an extension of probabilistic circuits from unstructured tensor data to tree-structured graph data. To this end, we use random finite sets to reflect a variable number of nodes and edges in the graph and to allow for exact and efficient inference. We demonstrate that our tractable model performs comparably to various intractable models based on neural networks.