Clustered task-aware meta-learning by learning from learning paths
To enable effective learning of new tasks with only a few examples, meta-learning acquires common knowledge from the existing tasks with a globally shared meta-learner. To further address the problem of task heterogeneity, recent developments balance between customization and generalization by incor...
Saved in:
Main Authors: | Peng, Danni, Pan, Sinno Jialin |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/172181 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Adaptive task sampling for meta-learning
by: LIU, Chenghao, et al.
Published: (2020) -
Generating personalized dialogue via multi-task meta-learning
by: Lee, Jing Yang, et al.
Published: (2021) -
Increasing motivation through task-based learning in Asean studies course
by: Nguyen, Thi Anh Thu
Published: (2017) -
Multi-task learning for sentiment analysis with hard-sharing and task recognition mechanisms
by: Zhang, Jian, et al.
Published: (2022) -
Meta-transfer learning for few-shot learning
by: SUN, Qianru, et al.
Published: (2019)