The neural attention mechanism plays an important role in many natural language processing applications. In particular, the use of multi-head attention extends single-head attention by allowing a model to jointly attend information from different perspectives. Without explicit constraining, however, multi-head attention may suffer from attention collapse, an issue that makes different heads extract similar attentive features, thus limiting the model's representation power. In this paper, for the first time, we provide a novel understanding of multi-head attention from a Bayesian perspective. Based on the recently developed particle-optimization sampling techniques, we propose a non-parametric approach that explicitly improves the repulsiveness in multi-head attention and consequently strengthens model's expressiveness. Remarkably, our Bayesian interpretation provides theoretical inspirations on the not-well-understood questions: why and how one uses multi-head attention. Extensive experiments on various attention models and applications demonstrate that the proposed repulsive attention can improve the learned feature diversity, leading to more informative representations with consistent performance improvement on various tasks.
Rethinking Graph Transformer Architecture Design for Node Classification
Zhejiang University of Technology（浙江工业大学）；Binjiang Institute of Artificial Intelligence, ZJUT（浙江工业大学滨江人工智能研究院）；Science and Technology on Communication Information Security Control Laboratory（通信信息安全控制实验室）
Rethinking Medical Landmark Localization with Prototype Learning-based Progressive Offset Correction
Shenzhen University（深圳大学）；Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人中心）；Boston Children’s Hospital（波士顿儿童医院）；Harvard Medical School（哈佛医学院）；School of Artificial Intelligence, Shenzhen University（深圳大学人工智能学院）；School of Biomedical Engineering and Informatics, Nanjing Medical University（南京医科大学生物医学工程与信息学院）；National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University（深圳大学大数据系统计算技术国家工程实验室）
