Continual Learning via Online Leverage Score Sampling

By D. Teng, Sakyasingha Dasgupta. 2019

5 citations recorded by the source corpus.

In order to mimic the human ability of continual acquisition and transfer of knowledge across various tasks, a learning system needs the capability for continual learning, effectively utilizing the previously acquired skills. As such, the key challenge is to transfer and generalize the knowledge learned from one task to other tasks, avoiding forgetting and interference of previous knowledge and improving the overall performance. In this paper, within the continual learning paradigm, we introduce a method that effectively forgets the less useful data samples continuously and allows beneficial information to be kept for training of the subsequent tasks, in an online manner. The method uses statistical leverage score information to measure the importance of the data samples in every task and adopts frequent directions approach to enable a continual or life-long learning property. This effectively maintains a constant training size across all tasks. We first provide mathematical intuition for the method and then demonstrate its effectiveness in avoiding catastrophic forgetting and computational efficiency on continual learning of classification tasks when compared with the existing state-of-the-art techniques.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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. Richard E. Turner
2. Tameem Adel
3. Han Zhao
4. Siddharth Swaroop
5. Thang D. Bui
6. Yarin Gal
7. Yingzhen Li
8. Jun Zhu

In Computer Vision and Pattern Recognition

1. Tameem Adel
2. Richard E. Turner
3. Han Zhao
4. Yarin Gal
5. Frederik Benzing
6. Qiang Liu
7. Max Welling
8. Fei Ye

Citations in the corpus

• Continual Learning with Adaptive Weights (CLAW) (2019, methodology): “The memory-based approach, which is the third influential approach to address the adaptationcatastrophic forgetting tradeoff, relies on episodic memory to store data (or pseudodata) from previous tasks (Ratcliff, 1990; Robins, 1993; 1995; Hattori, 2014; Rolnick et al., 2018; Teng & Dasgupta, 2019).”