Abstract Reasoning with Distracting Features
This work addresses the problem of abstract reasoning for AI systems, showing incremental improvements over existing methods.
The paper tackles the challenge of abstract reasoning in AI by addressing distracting features, proposing a feature robust abstract reasoning (FRAR) model that uses a reinforcement learning teacher to sequence training, resulting in state-of-the-art improvements of 18.7% on RAVEN and 13.3% on PGM datasets.
Abstraction reasoning is a long-standing challenge in artificial intelligence. Recent studies suggest that many of the deep architectures that have triumphed over other domains failed to work well in abstract reasoning. In this paper, we first illustrate that one of the main challenges in such a reasoning task is the presence of distracting features, which requires the learning algorithm to leverage counterevidence and to reject any of the false hypotheses in order to learn the true patterns. We later show that carefully designed learning trajectory over different categories of training data can effectively boost learning performance by mitigating the impacts of distracting features. Inspired by this fact, we propose feature robust abstract reasoning (FRAR) model, which consists of a reinforcement learning based teacher network to determine the sequence of training and a student network for predictions. Experimental results demonstrated strong improvements over baseline algorithms and we are able to beat the state-of-the-art models by 18.7% in the RAVEN dataset and 13.3% in the PGM dataset.