Relational Neurosymbolic Markov Models
This addresses the challenge of trustworthy AI deployment in sequential domains like reinforcement learning by providing a scalable method to enforce constraints, though it appears incremental as it builds on existing neurosymbolic frameworks.
The paper tackled the problem of scaling neurosymbolic AI for sequential tasks by introducing relational neurosymbolic Markov models, which provably satisfy constraints and scale better, solving problems beyond current state-of-the-art while maintaining interpretability and adaptability.
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 satisfaction of constraints necessary for trustworthy deployment. In contrast, neurosymbolic AI (NeSy) provides a sound formalism to enforce constraints in deep probabilistic models but scales exponentially on sequential problems. To overcome these limitations, we introduce relational neurosymbolic Markov models (NeSy-MMs), a new class of end-to-end differentiable sequential models that integrate and provably satisfy relational logical constraints. We propose a strategy for inference and learning that scales on sequential settings, and that combines approximate Bayesian inference, automated reasoning, and gradient estimation. Our experiments show that NeSy-MMs can solve problems beyond the current state-of-the-art in neurosymbolic AI and still provide strong guarantees with respect to desired properties. Moreover, we show that our models are more interpretable and that constraints can be adapted at test time to out-of-distribution scenarios.