paper-with-me

Papers

Self-Attention Attribution: Interpreting Information Interactions Inside Transformer

2020-04-23 · Yaru Hao, Li Dong, Furu Wei, Ke Xu

The great success of Transformer-based models benefits from the powerful multi-head self-attention mechanism, which learns token dependencies and encodes contextual information from the input. Prior work strives to attribute model decisions to individual input features with different saliency measures, but they fail to explain how these input features interact with each other to reach predictions. In this paper, we propose a self-attention attribution method to interpret the information interactions inside Transformer. We take BERT as an example to conduct extensive studies. Firstly, we apply self-attention attribution to identify the important attention heads, while others can be pruned with marginal performance degradation. Furthermore, we extract the most salient dependencies in each layer to construct an attribution tree, which reveals the hierarchical interactions inside Transformer. Finally, we show that the attribution results can be used as adversarial patterns to implement non-targeted attacks towards BERT.

📄 PDF Abstract BibTeX arXiv:2004.11207

Code (2)

YRdddream/attattr 공식 구현 pytorch
rohanshah13/attattr pytorch

Tasks

Attribute

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Transformer A Transformer is a model architecture that eschews recurrence and instead relies entirely on an [attention…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Attributions All the Way Down? The Metagame of Interpretability

2026-05-07 · Hubert Baniecki, Przemyslaw Biecek, Fabian Fumagalli arxiv

We introduce the metagame, a conceptual framework for quantifying second-order interaction effects of model explanations. For any first-order attribution $φ(f)$ explaining a model $f$, we measure the directional influenc…

Towards Faithful Neural Network Intrinsic Interpretation with Shapley Additive Self-Attribution

2023-09-27 · Ying Sun, HengShu Zhu, Hui Xiong

Self-interpreting neural networks have garnered significant interest in research. Existing works in this domain often (1) lack a solid theoretical foundation ensuring genuine interpretability or (2) compromise model expr…

Measuring the Mixing of Contextual Information in the Transformer

2022-03-08 · Javier Ferrando, Gerard I. Gállego, Marta R. Costa-jussà

The Transformer architecture aggregates input information through the self-attention mechanism, but there is no clear understanding of how this information is mixed across the entire model. Additionally, recent works hav…

GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers

2022-01-16 · ACL ARR January 2022 1 · Anonymous

There has been a growing interest in interpreting the underlying dynamics of Transformers. While self-attention patterns were initially deemed as the primary choice, recent studies have shown that integrating other compo…

GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers

2022-05-06 · NAACL 2022 7 · Ali Modarressi, Mohsen Fayyaz, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar

There has been a growing interest in interpreting the underlying dynamics of Transformers. While self-attention patterns were initially deemed as the primary option, recent studies have shown that integrating other compo…