Dacheng Tao, Tongliang Liu, Li Shen, Chun Yuan, Zhenyi Wang, Zixuan Hu
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.
The goal of data-free meta-learning is to learn useful prior knowledge from a collection of pre-trained models without accessing their training data. However, existing works only solve the problem in parameter space, which (i) ignore the fruitful data knowledge contained in the pretrained models; (ii) can not scale to large-scale pre-trained models; (iii) can only meta-learn pre-trained models with the same network architecture. To address those issues, we propose a unified framework, dubbed PURER, which contains: (1) ePisode cUrriculum inveRsion (ECI) during datafree meta training; and (2) invErsion calibRation following inner loop (ICFIL) during meta testing. During meta training, we propose ECI to perform pseudo episode training for learning to adapt fast to new unseen tasks. Specifically, we progressively synthesize a sequence of pseudo episodes by distilling the training data from each pre-trained model. The ECI adaptively increases the difficulty level of pseudo episodes according to the real-time feedback of the meta model. We formulate the optimization process of meta training with ECI as an adversarial form in an end-to-end manner. During meta testing, we further propose a simple plugand-play supplement-ICFIL-only used during meta testing to narrow the gap between meta training and meta testing task distribution. Extensive experiments in various realworld scenarios show the superior performance of ours.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2303.11183")
get_code_for_paper("2303.11183")
have("2303.11183")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2303.11183.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2303.11183)
Connect an agent — have() is free.