Multi-Viewpoint and Multi-Evaluation With Felicitous Inductive Bias Boost Machine Abstract Reasoning Ability

Abstract

Great efforts have been made to investigate AI’s ability in abstract reasoning, along with the proposal of various versions of RAVEN’s progressive matrices (RPM) as benchmarks. Previous studies suggest that, even after extensive training, neural networks may still struggle to make decisive decisions regarding RPM problems without sophisticated designs or additional semantic information in the form of meta-data. Through comprehensive experiments, we demonstrate that neural networks endowed with appropriate inductive biases, either intentionally designed or fortuitously matched, can efficiently solve RPM problems without the need for extra meta-data augmentation. Our work also reveals the importance of employing a multi-viewpoint with multi-evaluation approach as a key learning strategy for successful reasoning. Nevertheless, we acknowledge the unique role of metadata by demonstrating that a pre-training model supervised by meta-data leads to an RPM solver with improved performance. Codes are available in: https://github.com/QinglaiWeiCASIA/RavenSolver.