Timezone: »

DualHSIC: HSIC-Bottleneck and Alignment for Continual Learning
Zifeng Wang · Zheng Zhan · Yifan Gong · Yucai Shao · Stratis Ioannidis · Yanzhi Wang · Jennifer Dy

Wed Jul 26 02:00 PM -- 03:30 PM (PDT) @ Exhibit Hall 1 #505

Rehearsal-based approaches are a mainstay of continual learning (CL). They mitigate the catastrophic forgetting problem by maintaining a small fixed-size buffer with a subset of data from past tasks. While most rehearsal-based approaches exploit the knowledge from buffered past data, little attention is paid to inter-task relationships and to critical task-specific and task-invariant knowledge. By appropriately leveraging inter-task relationships, we propose a novel CL method, named DualHSIC, to boost the performance of existing rehearsal-based methods in a simple yet effective way. DualHSIC consists of two complementary components that stem from the so-called Hilbert Schmidt independence criterion (HSIC): HSIC-Bottleneck for Rehearsal (HBR) lessens the inter-task interference and HSIC Alignment (HA) promotes task-invariant knowledge sharing. Extensive experiments show that DualHSIC can be seamlessly plugged into existing rehearsal-based methods for consistent performance improvements, outperforming recent state-of-the-art regularization-enhanced rehearsal methods.

Author Information

Zifeng Wang (Northeastern University)
Zheng Zhan (Northeastern University)
Yifan Gong (Northeastern University)
Yucai Shao (University of California, Los Angeles)
Stratis Ioannidis (Northeastern University)
Yanzhi Wang (Northeastern University)
Jennifer Dy (Northeastern University)

More from the Same Authors