Attention computes the dependency between representations, and it encourages the model to focus on the important selective features. Attention-based models, such as Transformer and graph attention network (GAT), are widely utilized for sequential data and graph-structured data. This paper suggests a new interpretation and generalized structure of the attention in Transformer and GAT. For the attention in Transformer and GAT, we derive that the attention is a product of two parts: 1) the RBF kernel to measure the similarity of two instances and 2) the exponential of L2 norm to compute the importance of individual instances. From this decomposition, we generalize the attention in three ways. First, we propose implicit kernel attention with an implicit kernel function instead of manual kernel selection. Second, we generalize L2 norm as the Lp norm. Third, we extend our attention to structured multi-head attention. Our generalized attention shows better performance on classification, translation, and regression tasks.
|Title of host publication||35th AAAI Conference on Artificial Intelligence, AAAI 2021|
|Publisher||Association for the Advancement of Artificial Intelligence|
|Number of pages||9|
|Publication status||Published - 2021|
|Event||35th AAAI Conference on Artificial Intelligence, AAAI 2021 - Virtual, Online|
Duration: 2021 Feb 2 → 2021 Feb 9
|Name||35th AAAI Conference on Artificial Intelligence, AAAI 2021|
|Conference||35th AAAI Conference on Artificial Intelligence, AAAI 2021|
|Period||21/2/2 → 21/2/9|
Bibliographical noteFunding Information:
This research was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Education(NRF-2018R1C1B600865213)
Copyright © 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
All Science Journal Classification (ASJC) codes
- Artificial Intelligence