ScholarGate
助手
Machine learningDeep learning / NLP / CV

可解释 Transformer

可解释 Transformer 将标准或预训练的 Transformer 架构与事后或内置的可解释性技术（如注意力展开、梯度加权注意力或 SHAP）相结合，以揭示哪些输入 token 或区域驱动了每个预测。该方法弥合了高预测准确性与高风险或受监管领域所需的透明度之间的差距。

在 MethodMind 中打开即将推出视频即将推出Download slides

阅读完整方法

仅限会员

使用免费账户登录即可阅读本节。

登录

Method map

The neighbourhood of related methods — select a node to explore.

可解释 Transformer
[需翻译标题：BERT-based Classi…可解释的BERT分类多模态Transformer自监督Transformer可解释图神经网络可解释门控循环单元 (Explainable G…可解释长短期记忆网络可解释多层感知机可解释命名实体识别可解释问答

+4 more

来源

  1. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30. link ↗
  2. Chefer, H., Gur, S., & Wolf, L. (2021). Transformer interpretability beyond attention visualization. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 782–791. DOI: 10.1109/CVPR46437.2021.00084 ↗

如何引用本页

ScholarGate. (2026, June 3). Explainable Transformer (Interpretability-Augmented Transformer Model). ScholarGate. https://scholargate.app/zh/deep-learning/explainable-transformer

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side →

被引用于

可解释的BERT分类可解释图神经网络可解释门控循环单元 (Explainable GRU)可解释长短期记忆网络可解释多层感知机可解释命名实体识别可解释问答可解释循环神经网络可解释的 RoBERTa 分类可解释句子嵌入可解释文本摘要

发现本页有问题？报告或提出修改建议 →

ScholarGate — Explainable Transformer (Explainable Transformer (Interpretability-Augmented Transformer Model)). 于 2026-06-15 检索自 https://scholargate.app/zh/deep-learning/explainable-transformer · 数据集： https://doi.org/10.5281/zenodo.20539026