Sum-product networks: A new deep architecture

The key limiting factor in graphical model inference and learning is the complexity of the partition function. We thus ask the question: what are the most general conditions under which the partition function is tractable? The answer leads to a new kind of deep architecture, which we call sum-product networks (SPNs) and will present in this abstract.

• Publication year

  2011

• Venue

  IEEE International Conference on Computer Vision

• Publication date

  2011-07-14

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1109/ICCVW.2011.6130310arXiv 1202.3732
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Importance sampling-based estimation over AND/OR search spaces for graphical models

  2012cited by this paper
• An Efficient Learning Procedure for Deep Boltzmann Machines

  2012cited by this paper
• Unsupervised Learning of Probabilistic Grammar-Markov Models for Object Categories

  2011cited by this paper
• Object detection grammars

  2011cited by this paper
• Learning Efficient Markov Networks

  2010cited by this paper
• Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations

  2009influential reference
• Learning the Structure of Deep Sparse Graphical Models

  2009cited by this paper
• Learning multi-linear representations of distributions for efficient inference

  2009cited by this paper
• Deep Boltzmann Machines

  2009cited by this paper
• Learning Arithmetic Circuits

  2008cited by this paper
• Learning Deep Architectures for AI

  2007cited by this paper
• Scene Completion Using Millions of Photographs

  2007cited by this paper
• Efficient Principled Learning of Thin Junction Trees

  2007cited by this paper
• Mixtures of hierarchical topics with Pachinko allocation

  2007cited by this paper
• Supporting Online Material for Reducing the Dimensionality of Data with Neural Networks

  2006influential reference
• Naive Bayes models for probability estimation

  2005cited by this paper
• Case-factor diagrams for structured probabilistic modeling

  2004cited by this paper
• On Bias, Variance, 0/1—Loss, and the Curse-of-Dimensionality

  2004cited by this paper
• Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories

  2004cited by this paper
• Head-Driven Statistical Models for Natural Language Parsing

  2003cited by this paper
• Hierarchical latent class models for cluster analysis

  2002cited by this paper
• Random Forests

  2001cited by this paper
• Image inpainting

  2000cited by this paper
• A differential approach to inference in Bayesian networks

  2000influential reference
• Hierarchical models of object recognition in cortex

  1999cited by this paper
• A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants

  1998cited by this paper
• Parameterisation of a Stochastic Model for Human Face Identi cation

  1994cited by this paper
• Parameterisation of a stochastic model for human face identification

  1994cited by this paper
• On bias.

  1994cited by this paper
• A new view of the EM algorithm that justifies incremental and other variants

  1993cited by this paper
• Eigenfaces for Recognition

  1991cited by this paper
• Learning DNF by Decision Trees

  1989cited by this paper
• Probabilistic reasoning in intelligent systems - networks of plausible inference

  1989cited by this paper
• Backpropagation Applied to Handwritten Zip Code Recognition

  1989cited by this paper
• Probabilistic reasoning in intelligent systems

  1988cited by this paper
• Feature Discovery by Competive Learning

  1986cited by this paper
• A general framework for parallel distributed processing

  1986cited by this paper
• Learning internal representations by error propagation

  1986cited by this paper

• To Neuro-Symbolic Classification and Beyond by Compiling Description Logic Ontologies to Probabilistic Circuits

  2026cites this paper
• Deep probabilistic circuits for efficient uncertainty handling in learning systems

  2026influential citation
• Breaking the Factorization Barrier in Diffusion Language Models

  2026cites this paper
• Certifiable Boolean Reasoning Is Universal

  2026cites this paper
• PAR: Plausibility-aware Amortized Recourse Generation

  2026cites this paper
• Probably Approximately Correct Maximum A Posteriori Inference

  2026cites this paper
• LogSumExp: Efficient Approximate Logarithm Acceleration for Embedded Tractable Probabilistic Reasoning

  2026cites this paper
• Causal Neural Probabilistic Circuits

  2026cites this paper
• Reactive Knowledge Representation and Asynchronous Reasoning

  2026cites this paper
• ESTroM: Element-Flow Architecture for Processing Sparse Tractable Probabilistic Models

  2026cites this paper
• CUBE: A Cardinality Estimator Based on Neural CDF

  2025cites this paper
• Backpropagation from KL Projections: Differential and Exact I-Projection Correspondences

  2025cites this paper
• Evaluating Learned Query Performance Prediction Models at LinkedIn: Challenges, Opportunities, and Findings

  2025cites this paper
• Tractable Generative Modelling of Cosmological Numerical Simulations

  2025cites this paper
• QuantTPM: Efficient Mixed-Precision Quantization Framework for Tractable Probabilistic Models

  2025cites this paper
• An Approach Based on Sum Product Networks for Code Smells Detection

  2025cites this paper
• Tractable Representation Learning with Probabilistic Circuits

  2025cites this paper
• A Unified Model for Cardinality Estimation by Learning from Data and Queries via Sum-Product Networks

  2025cites this paper
• Rethinking Probabilistic Circuit Parameter Learning

  2025influential citation
• Distillation of a tractable model from the VQ-VAE

  2025cites this paper
• Tractable Probabilistic Models for Investment Planning

  2025cites this paper
• On the Hardness of Approximating Distributions with Tractable Probabilistic Models

  2025cites this paper
• How to Square Tensor Networks and Circuits Without Squaring Them

  2025cites this paper
• A Robust Attention-based Cardinality Estimator with Domain Adaptation

  2025cites this paper
• Exact Inference for Quantum Circuits: A Testing Oracle for Quantum Software Stacks

  2025cites this paper
• Privacy-Preserving Range Aggregation Queries Using a Learning-Based Approach

  2025cites this paper
• uGMM-NN: Univariate Gaussian Mixture Model Neural Network

  2025cites this paper
• FAAQP: Fast and Accurate Approximate Query Processing based on Bitmap-augmented Sum-Product Network

  2025cites this paper
• Tractable probabilistic models and computational complexity

  2025influential citation
• On the Hardness of Approximating Distributions with Probabilistic Circuits

  2025cites this paper
• Solving Satisfiability Modulo Counting Exactly with Probabilistic Circuits

  2025cites this paper
• CausalMan: A physics-based simulator for large-scale causality

  2025cites this paper
• ACE: A Cardinality Estimator for Set-Valued Queries

  2025cites this paper
• GRELA: Exploiting graph representation learning in effective approximate query processing

  2025cites this paper
• Enhancing and Evaluating Probabilistic Circuits for High-Resolution Lossless Image Compression

  2025cites this paper
• Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits

  2025cites this paper
• Deep Polynomial Chaos Expansion

  2025cites this paper
• Sketched Sum-Product Networks for Joins

  2025cites this paper
• SUPN: Shallow Universal Polynomial Networks

  2025cites this paper
• On the Optimization Landscape of Low Rank Adaptation Methods for Large Language Models

  2025cites this paper
• Counterfactual Explanations in Medical Imaging: Exploring SPN-Guided Latent Space Manipulation

  2025cites this paper
• Tractable Sharpness-Aware Learning of Probabilistic Circuits

  2025cites this paper
• Soft learning probabilistic circuits

  2025cites this paper
• The DeepLog Neurosymbolic Machine

  2025cites this paper
• Structural Causal Circuits: Probabilistic Circuits Climbing All Rungs of Pearl's Ladder of Causation

  2025influential citation
• N-Parties Private Structure and Parameter Learning for Sum-Product Networks

  2025influential citation
• The Limits of Tractable Marginalization

  2025cites this paper
• OBDDs, SDDs, and circuits of bounded width: Completeness matters

  2025cites this paper
• Causality, Machine Learning, and Feature Selection: A Survey

  2025cites this paper
• Scaling Probabilistic Circuits via Data Partitioning

  2025cites this paper
• A Quantum Information Theoretic Approach to Tractable Probabilistic Models

  2025cites this paper
• AutoPC: An Open-Source Framework for Efficient Probabilistic Reasoning on FPGA Hardware

  2024cites this paper
• What is the Relationship between Tensor Factorizations and Circuits (and How Can We Exploit it)?

  2024influential citation
• Self-adaptive smoothing model for cardinality estimation

  2024cites this paper
• GraphSPNs: Sum-Product Networks Benefit From Canonical Orderings

  2024cites this paper
• Optimal Transport for Probabilistic Circuits

  2024cites this paper
• Plant Disease Recognition: A Comprehensive Mini Review

  2024cites this paper
• Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs

  2024influential citation
• Using sum product networks to predict defects in software systems

  2024cites this paper
• On the Expressive Power of Tree-Structured Probabilistic Circuits

  2024cites this paper
• On the Relationship Between Monotone and Squared Probabilistic Circuits

  2024cites this paper
• Causal Learning in Biomedical Applications: A Benchmark

  2024cites this paper
• Probabilistic Circuits for Cumulative Distribution Functions

  2024cites this paper
• Top-Down Bayesian Posterior Sampling for Sum-Product Networks

  2024influential citation
• Efficient Hardware Accelerator Based on Medium Granularity Dataflow for SpTRSV

  2024cites this paper
• Causal Learning in Biomedical Applications

  2024cites this paper
• Scaling Continuous Latent Variable Models as Probabilistic Integral Circuits

  2024cites this paper
• Learning Distributionally Robust Tractable Probabilistic Models in Continuous Domains

  2024cites this paper
• On the Robustness and Reliability of Late Multi-Modal Fusion using Probabilistic Circuits

  2024cites this paper
• χSPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains

  2024cites this paper
• StarfishDB: A Query Execution Engine for Relational Probabilistic Programming

  2024cites this paper
• A novel graph oversampling framework for node classification in class-imbalanced graphs

  2024cites this paper
• Privacy-Enhanced Database Synthesis for Benchmark Publishing

  2024cites this paper
• A Circus of Circuits: Connections Between Decision Diagrams, Circuits, and Automata

  2024cites this paper
• Probabilistic Generating Circuits - Demystified

  2024cites this paper
• Causal Unit Selection using Tractable Arithmetic Circuits

  2024cites this paper
• Probabilistic Neural Circuits

  2024cites this paper
• On Hardware-efficient Inference in Probabilistic Circuits

  2024cites this paper
• PRICE: A Pretrained Model for Cross-Database Cardinality Estimation

  2024influential citation
• Polynomial Semantics of Tractable Probabilistic Circuits

  2024influential citation
• Probabilistic Circuits with Constraints via Convex Optimization

  2024cites this paper
• Soft Learning Probabilistic Circuits

  2024cites this paper
• Structured d-DNNF Is Not Closed Under Negation

  2024cites this paper
• Attribute imputation autoencoders for attribute-missing graphs

  2024cites this paper
• Neural Network Approximators for Marginal MAP in Probabilistic Circuits

  2024influential citation
• Building Expressive and Tractable Probabilistic Generative Models: A Review

  2024influential citation
• Probabilistic ML Verification via Weighted Model Integration

  2024cites this paper
• Credibility-Aware Multi-Modal Fusion Using Probabilistic Circuits

  2024cites this paper
• DT-SIM: Property-Based Testing for MPC Security

  2024cites this paper
• Deep Tractable Probabilistic Models

  2024cites this paper
• Causality and tractable probabilistic models

  2024cites this paper
• Generating Likely Counterfactuals Using Sum-Product Networks

  2024cites this paper
• Exploring Sum-Product Networks for Image Classification. Applications

  2024cites this paper
• Restructuring Tractable Probabilistic Circuits

  2024cites this paper
• Scaling Tractable Probabilistic Circuits: A Systems Perspective

  2024influential citation
• Not all Strongly Rayleigh Distributions Have Small Probabilistic Generating Circuits

  2023cites this paper
• Tractable and Expressive Generative Models of Genetic Variation Data

  2023cites this paper
• Continuously Parameterized Mixture Models

  2023influential citation
• Probabilistic Flow Circuits: Towards Unified Deep Models for Tractable Probabilistic Inference Supplementary Material

  2023cites this paper
• Bayesian Learning of Probabilistic Circuits with Domain Constraints

  2023cites this paper