Concepts, Properties and an Approach for Compositional Generalization
This work aims to clarify fundamental concepts of compositional generalization for AI researchers, potentially leading to advancements in artificial intelligence.
This paper addresses the problem of compositional generalization, which is the ability to understand novel combinations from known components. It presents an approach that uses architecture design and regularization to regulate information in representations.
Compositional generalization is the capacity to recognize and imagine a large amount of novel combinations from known components. It is a key in human intelligence, but current neural networks generally lack such ability. This report connects a series of our work for compositional generalization, and summarizes an approach. The first part contains concepts and properties. The second part looks into a machine learning approach. The approach uses architecture design and regularization to regulate information of representations. This report focuses on basic ideas with intuitive and illustrative explanations. We hope this work would be helpful to clarify fundamentals of compositional generalization and lead to advance artificial intelligence.