Shaolei Ren, Wang Zhu, Yejia Liu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Continual learning faces a crucial challenge of catastrophic forgetting. To address this challenge, experience replay (ER) that maintains a tiny subset of samples from previous tasks has been commonly used. Existing ER works usually focus on refining the learning objective for each task with a static memory construction policy. In this paper, we formulate the dynamic memory construction in ER as a combinatorial optimization problem, which aims at directly minimizing the global loss across all experienced tasks. We first apply three tactics to solve the problem in the offline setting as a starting point. To provide an approximate solution to this problem in the online continual learning setting, we further propose the Global Pseudo-task Simulation (GPS), which mimics future catastrophic forgetting of the current task by permutation. Our empirical results and analyses suggest that the GPS consistently improves accuracy across four commonly used vision benchmarks. We have also shown that our GPS can serve as the unified framework for integrating various memory construction policies in existing ER works.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2210.08442")
get_code_for_paper("2210.08442")
have("2210.08442")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2210.08442.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2210.08442)
Connect an agent — have() is free.