Sum-product networks: A survey
arXiv:2004.01167
Abstract
A sum-product network (SPN) is a probabilistic model, based on a rooted acyclic directed graph, in which terminal nodes represent univariate probability distributions and non-terminal nodes represent convex combinations (weighted sums) and products of probability functions. They are closely related to probabilistic graphical models, in particular to Bayesian networks with multiple context-specific independencies. Their main advantage is the possibility of building tractable models from data, i.e., models that can perform several inference tasks in time proportional to the number of links in the graph. They are somewhat similar to neural networks and can address the same kinds of problems, such as image processing and natural language understanding. This paper offers a survey of SPNs, including their definition, the main algorithms for inference and learning from data, the main applications, a brief review of software libraries, and a comparison with related models
arXiv comment24 pages, 6 figures, 97 references
References in corpus (20)
- Context-Specific Independence in Bayesian Networks
- Sum-Product Networks: A New Deep Architecture
- MAP Complexity Results and Approximation Methods
- Learning Arithmetic Circuits
- On the Robustness of Most Probable Explanations
- SPFlow: An Easy and Extensible Library for Deep Probabilistic Learning using Sum-Product Networks
- A Unified Approach for Learning the Parameters of Sum-Product Networks
- On Relaxing Determinism in Arithmetic Circuits
- Bayesian Learning of Sum-Product Networks
- DeepDB: Learn from Data, not from Queries!
- Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures
- Tractable Querying and Learning in Hybrid Domains via Sum-Product Networks
- Online Structure Learning for Sum-Product Networks with Gaussian Leaves
- Sum-Product-Quotient Networks
- Sum-Product Networks for Sequence Labeling
- Maximum A Posteriori Inference in Sum-Product Networks
- Learning Arbitrary Sum-Product Network Leaves with Expectation-Maximization
- Deep Generalized Convolutional Sum-Product Networks
- Deep Compression of Sum-Product Networks on Tensor Networks
- Linear Time Computation of Moments in Sum-Product Networks