Solving Raven's Progressive Matrices with Multi-Layer Relation Networks
This work addresses the problem of relational reasoning in machine learning systems, particularly for AI researchers, by significantly advancing performance on a key benchmark.
The paper tackled the challenge of solving Raven's Progressive Matrices, a difficult relational reasoning benchmark, by combining Wild Relation Networks with Multi-Layer Relation Networks and introducing Magnitude Encoding, achieving an accuracy of 98.0% compared to the previous state-of-the-art of 62.6%.
Raven's Progressive Matrices are a benchmark originally designed to test the cognitive abilities of humans. It has recently been adapted to test relational reasoning in machine learning systems. For this purpose the so-called Procedurally Generated Matrices dataset was set up, which is so far one of the most difficult relational reasoning benchmarks. Here we show that deep neural networks are capable of solving this benchmark, reaching an accuracy of 98.0 percent over the previous state-of-the-art of 62.6 percent by combining Wild Relation Networks with Multi-Layer Relation Networks and introducing Magnitude Encoding, an encoding scheme designed for late fusion architectures.