将逻辑约束融入序列模型，实现可信赖的可解释推理
Relational Neurosymbolic Markov Models
- 用神经符号方法构建可微分序列模型，保证关系逻辑约束
- 在多种任务上超越现有神经符号模型，且支持测试时动态调整约束
- 适合需要可解释性与可靠性保障的应用场景
序列问题在人工智能中广泛存在，如强化学习和自然语言处理。当前主流深度序列模型（如Transformer）虽性能优越，但无法保证部署所需的约束满足。而神经符号AI（NeSy）虽能形式化约束，却在序列问题上面临指数级扩展瓶颈。为此，我们提出关系型神经符号马尔可夫模型（NeSy-MMs），一种端到端可微的序列模型，能集成并严格满足关系逻辑约束。通过结合近似贝叶斯推断、自动推理与梯度估计，该方法实现了高效推理与学习。实验表明，NeSy-MMs可在超出当前神经符号模型能力范围的任务上取得成功，并提供对预期属性的强保证。此外，模型更具可解释性，且约束可在测试时动态适应分布外场景。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。