Causal-Symbolic Meta-Learning (CSML): Inducing Causal World Models for Few-Shot Generalization
This addresses the challenge of sample-efficient learning for AI systems, though it is incremental as it builds on existing meta-learning and neuro-symbolic approaches.
The paper tackles the problem of poor generalization in deep learning by proposing Causal-Symbolic Meta-Learning (CSML), a framework that learns latent causal structures to enable few-shot adaptation, and it shows dramatic outperformance over state-of-the-art baselines on tasks requiring causal inference.
Modern deep learning models excel at pattern recognition but remain fundamentally limited by their reliance on spurious correlations, leading to poor generalization and a demand for massive datasets. We argue that a key ingredient for human-like intelligence-robust, sample-efficient learning-stems from an understanding of causal mechanisms. In this work, we introduce Causal-Symbolic Meta-Learning (CSML), a novel framework that learns to infer the latent causal structure of a task distribution. CSML comprises three key modules: a perception module that maps raw inputs to disentangled symbolic representations; a differentiable causal induction module that discovers the underlying causal graph governing these symbols and a graph-based reasoning module that leverages this graph to make predictions. By meta-learning a shared causal world model across a distribution of tasks, CSML can rapidly adapt to novel tasks, including those requiring reasoning about interventions and counterfactuals, from only a handful of examples. We introduce CausalWorld, a new physics-based benchmark designed to test these capabilities. Our experiments show that CSML dramatically outperforms state-of-the-art meta-learning and neuro-symbolic baselines, particularly on tasks demanding true causal inference.