Wei Wu, Chen Zhang, Jingang Wang, Dawei Song, Lei Ren
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.
Prompt-tuning has shown appealing performance in few-shot classification by virtue of its capability in effectively exploiting pre-trained knowledge. This motivates us to check the hypothesis that prompt-tuning is also a promising choice for long-tailed classification, since the tail classes are intuitively few-shot ones. To achieve this aim, we conduct empirical studies to examine the hypothesis. The results demonstrate that prompt-tuning makes pretrained language models at least good long-tailed learners. For intuitions on why prompt-tuning can achieve good performance in long-tailed classification, we carry out in-depth analyses by progressively bridging the gap between prompttuning and commonly used finetuning. The summary is that the classifier structure and parameterization form the key to making good long-tailed learners, in comparison with the less important input structure. Finally, we verify the applicability of our finding to few-shot classification. 1 Jingang Wang and Dawei Song are the corresponding authors. 1 Good long-tailed learners are abbreviated as GLEE.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2205.05461")
get_code_for_paper("2205.05461")
have("2205.05461")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2205.05461.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2205.05461)
Connect an agent — have() is free.