arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.14014cs.LGcs.AIcs.CL
收藏

What Dense Graph Do You Need for Self-Attention?

Fudan University(复旦大学);Peng Cheng Laboratory(鹏城实验室)

Yuxin Wang, Chu-Tak Lee, Qipeng Guo, Zhangyue Yin, Yunhua Zhou, Xuanjing Huang, Xipeng Qiu

英文摘要:

Transformers have made progress in miscellaneous tasks, but suffer from quadratic computational and memory complexities. Recent works propose sparse Transformers with attention on sparse graphs to reduce complexity and remain strong performance. While effective, the crucial parts of how dense a graph needs to be to perform well are not fully explored. In this paper, we propose Normalized Information Payload (NIP), a graph scoring function measuring information transfer on graph, which provides an analysis tool for trade-offs between performance and complexity. Guided by this theoretical analysis, we present Hypercube Transformer, a sparse Transformer that models token interactions in a hypercube and shows comparable or even better results with vanilla Transformer while yielding $O(N\log N)$ complexity with sequence length $N$. Experiments on tasks requiring various sequence lengths lay validation for our graph function well.

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。

↑