What is Next when Sequential Prediction Meets Implicitly Hard Interaction?
Kaixi Hu, Lin Li, Qing Xie, Jianquan Liu, Xiaohui Tao
Abstract
Hard interaction learning between source sequences and their next targets is challenging, which exists in a myriad of sequential prediction tasks. During the training process, most existing methods focus on explicitly hard interactions caused by wrong responses. However, a model might conduct correct responses by capturing a subset of learnable patterns, which results in implicitly hard interactions with some unlearned patterns. As such, its generalization performance is weakened. The problem gets more serious in sequential prediction due to the interference of substantial similar candidate targets.
Topics & Concepts
GeneralizationComputer scienceFocus (optics)Process (computing)Artificial intelligenceMachine learningInterference (communication)Theoretical computer scienceMathematicsProgramming languageChannel (broadcasting)PhysicsComputer networkMathematical analysisOpticsMachine Learning and Data ClassificationDomain Adaptation and Few-Shot LearningHuman Pose and Action Recognition