2023 · 24 citations · 25 references
ComputingComputer ScienceArtificial IntelligenceKnowledge RepresentationMachine LearningAutomated ReasoningDeep LearningNatural Language UnderstandingNeural NetworksSymbolic SystemsCitation Network ModelingCitation Network StructureEmpirical EvaluationEnergy-based ModelsParameter LearningProbabilistic Deep LearningProbabilistic LogicReasoning Models
In this paper, we introduce Neural Probabilistic Soft Logic (NeuPSL), a novel neuro-symbolic (NeSy) framework that unites state-of-the-art symbolic reasoning with the low-level perception of deep neural networks. To model the boundary between neural and symbolic representations, we propose a family of energy-based models, NeSy Energy-Based Models, and show that they are general enough to include NeuPSL and many other NeSy approaches. Using this framework, we show how to seamlessly integrate neural and symbolic parameter learning and inference in NeuPSL. Through an extensive empirical evaluation, we demonstrate the benefits of using NeSy methods, achieving upwards of 30% improvement over independent neural network models. On a well-established NeSy task, MNIST-Addition, NeuPSL demonstrates its joint reasoning capabilities by outperforming existing NeSy approaches by up to 10% in low-data settings. Furthermore, NeuPSL achieves a 5% boost in performance over state-of-the-art NeSy methods in a canonical citation network task with up to a 40 times speed up.
25
Collective Classification in Network Data
Prithviraj Sen, Galileo Namata, Mustafa Bilgic et al. · AI Magazine · 2008 · 3.3K citations · Full text
Fuzzy sets and fuzzy logic: theory and applications
Choice Reviews Online · 1996 · 1.9K citations
Simplifying Graph Convolutional Networks
Felix Wu, Tianyi Zhang, Amauri H. Souza et al. · arXiv (Cornell University) · 2019 · 1.2K citations · Full text