AttentionViz：Transformer注意力的全局视图
AttentionViz: A Global View of Transformer Attention
AI总结：
本文提出AttentionViz交互式可视化工具，通过联合嵌入query和key向量揭示Transformer注意力的全局模式，并验证其在语言和视觉模型理解中的价值。
摘要：
Transformer模型正在革新机器学习，但其内部工作机制仍然神秘。在这项工作中，我们提出了一种新的可视化技术，旨在帮助研究人员理解Transformer中的自注意力机制，该机制使这些模型能够学习序列元素之间丰富的上下文关系。我们方法背后的主要思想是将Transformer模型用于计算注意力的query和key向量进行联合嵌入可视化。与以往的注意力可视化技术不同，我们的方法能够分析跨多个输入序列的全局模式。我们基于这些联合的query-key嵌入创建了一个交互式可视化工具AttentionViz（演示地址：http://attentionviz.com），并使用它来研究语言和视觉Transformer中的注意力机制。我们通过若干应用场景和专家反馈，证明了我们的方法在提升模型理解以及提供关于query-key交互的新见解方面的实用性。
英文摘要：
Transformer models are revolutionizing machine learning, but their inner workings remain mysterious. In this work, we present a new visualization technique designed to help researchers understand the self-attention mechanism in transformers that allows these models to learn rich, contextual relationships between elements of a sequence. The main idea behind our method is to visualize a joint embedding of the query and key vectors used by transformer models to compute attention. Unlike previous attention visualization techniques, our approach enables the analysis of global patterns across multiple input sequences. We create an interactive visualization tool, AttentionViz (demo: http://attentionviz.com), based on these joint query-key embeddings, and use it to study attention mechanisms in both language and vision transformers. We demonstrate the utility of our approach in improving model understanding and offering new insights about query-key interactions through several application scenarios and expert feedback.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
