paper-with-me

Papers

A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference

2023-09-21 · NeurIPS 2023 11

We study the problem of combining neural networks with symbolic reasoning. Recently introduced frameworks for Probabilistic Neurosymbolic Learning (PNL), such as DeepProbLog, perform exponential-time exact inference, limiting the scalability of PNL solutions. We introduce Approximate Neurosymbolic Inference (A-NeSI): a new framework for PNL that uses neural networks for scalable approximate inference. A-NeSI 1) performs approximate inference in polynomial time without changing the semantics of probabilistic logics; 2) is trained using data generated by the background knowledge; 3) can generate symbolic explanations of predictions; and 4) can guarantee the satisfaction of logical constraints at test time, which is vital in safety-critical applications. Our experiments show that A-NeSI is the first end-to-end method to solve three neurosymbolic tasks with exponential combinatorial scaling. Finally, our experiments show that A-NeSI achieves explainability and safety without a penalty in performance.

📄 PDF Abstract BibTeX

Code (1)

hemile/a-nesi 공식 구현 pytorch

Similar Papers 제목 키워드 기반

CTSketch: Compositional Tensor Sketching for Scalable Neurosymbolic Learning

2025-03-31 · Seewon Choi, Alaia Solko-Breslin, Rajeev Alur, Eric Wong

Many computational tasks benefit from being formulated as the composition of neural networks followed by a discrete symbolic program. The goal of neurosymbolic learning is to train the neural networks using only end-to-e…

EM-NeSy: Expectation Maximization for Neurosymbolic Learning

2026-06-12 · Annegret Seibt, Luc De Raedt, Giuseppe Marra arxiv

Neurosymbolic (NeSy) models integrate neural networks and symbolic reasoning for robust and interpretable AI. State-of-the-art NeSy models require that the symbolic component is expressed in a differentiable way, often c…

Computational Efficiency

On Scaling Neurosymbolic Programming through Guided Logical Inference

2025-01-30 · Thomas Jean-Michel Valentin, Luisa Sophie Werner, Pierre Genevès, Nabil Layaïda

Probabilistic neurosymbolic learning seeks to integrate neural networks with symbolic programming. Many state-of-the-art systems rely on a reduction to the Probabilistic Weighted Model Counting Problem (PWMC), which requ…

Relational Neurosymbolic Markov Models

2024-12-17 · Lennert De Smet, Gabriele Venturato, Luc De Raedt, Giuseppe Marra

Sequential problems are ubiquitous in AI, such as in reinforcement learning or natural language processing. State-of-the-art deep sequential models, like transformers, excel in these settings but fail to guarantee the sa…

Bayesian Inference

On the Hardness of Probabilistic Neurosymbolic Learning

2024-06-06 · Jaron Maene, Vincent Derkinderen, Luc De Raedt

The limitations of purely neural learning have sparked an interest in probabilistic neurosymbolic models, which combine neural networks with probabilistic logical reasoning. As these neurosymbolic models are trained with…

Logical Reasoning