Neural Markov Logic Networks
arXiv:1905.13462
Abstract
We introduce neural Markov logic networks (NMLNs), a statistical relational learning system that borrows ideas from Markov logic. Like Markov logic networks (MLNs), NMLNs are an exponential-family model for modelling distributions over possible worlds, but unlike MLNs, they do not rely on explicitly specified first-order logic rules. Instead, NMLNs learn an implicit representation of such rules as a neural network that acts as a potential function on fragments of the relational structure. Similarly to many neural symbolic methods, NMLNs can exploit embeddings of constants but, unlike them, NMLNs work well also in their absence. This is extremely important for predicting in settings other than the transductive one. We showcase the potential of NMLNs on knowledge-base completion, triple classification and on generation of molecular (graph) data.
References in corpus (7)
- GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
- Learning Deep Generative Models of Graphs
- How Powerful are Graph Neural Networks?
- Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
- Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge
- RelNN: A Deep Neural Model for Relational Learning
- Relational Marginal Problems: Theory and Estimation
Cited by in corpus (6)
- Logic Tensor Networks
- Efficient Generation of Structured Objects with Constrained Adversarial Networks
- A Survey on Neural-symbolic Learning Systems
- Lossless Compression of Structured Convolutional Models via Lifting
- Does Symbolic Knowledge Prevent Adversarial Fooling?
- Relational Neural Markov Random Fields