Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignment

While Deep Neural Networks (DNNs) are deriving the major innovations in nearly every field through their powerful automation, we are also witnessing the peril behind automation as a form of bias, such as automated racism, gender bias, and adversarial bias. As the societal impact of DNNs grows, finding an effective way to steer DNNs to align their behavior with the human mental model has become indispensable in realizing fair and accountable models. We propose a novel framework of Interactive Attention Alignment (IAA) that aims at realizing human-steerable Deep Neural Networks (DNNs). IAA leverages DNN model explanation method as an interactive medium that humans can use to unveil the cases of biased model attention and directly adjust the attention. In improving the DNN using human-generated adjusted attention, we introduce GRADIA, a novel computational pipeline that jointly maximizes attention quality and prediction accuracy. We evaluated IAA framework in Study 1 and GRADIA in Study 2 in a gender classification problem. Study 1 found applying IAA can significantly improve the perceived quality of model attention from human eyes. In Study 2, we found using GRADIA can (1) significantly improve the perceived quality of model attention and (2) significantly improve model performance in scenarios where the training samples are limited. We present implications for future interactive user interfaces design towards human-alignable AI.