Memory Efficient Continual Learning for Neural Text Classification

By B. Ermiş, Giovanni Zappella, Martin Wistuba, Cédric Archambeau. 2022

5 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Martin Wistuba
2. Aditya Rawal
3. Cédric Archambeau
4. B. Ermiş
5. Giovanni Zappella
6. Xuezhi Wang
7. Yanzhe Zhang
8. Diyi Yang

In Computer Vision and Pattern Recognition

1. Aditya Rawal
2. B. Ermiş
3. Giovanni Zappella
4. Martin Wistuba
5. Cédric Archambeau
6. Diyi Yang
7. Yanzhe Zhang
8. Xuezhi Wang

In Radiology, Nuclear Medicine and Imaging

1. B. Ermiş
2. Martin Wistuba
3. Giovanni Zappella
4. Aditya Rawal

Citations in the corpus

• Continual Sequence Generation with Adaptive Compositional Modules (2022, methodology): “In language domain, prior work often utilizes adapter (Houlsby et al., 2019; Madotto et al., 2020; Ermis et al., 2022), which could be considered as task-specific MLPs inserted into frozen transformer layers.”
• Memory Efficient Continual Learning with Transformers (2022, methodology): “[16] Beyza Ermis, Giovanni Zappella, Martin Wistuba, and Cedric Archambeau.”
• Continual Learning with Transformers for Image Classification (2022, methodology): “In [9] they leverage two common methods for transferability estimation: (1) Log Expected Empirical Prediction (LEEP) [22] and (2) TransRate [13].”