用k-NN方法简单高效预测迁移学习效果
k-NN as a Simple and Effective Estimator of Transferability
- 用k-NN评估特征迁移性，无需复杂计算
- 在42000+实验中优于23种现有度量方法
- 适合快速评估新任务的迁移潜力
在领域偏移、任务变化、模型结构改变的新场景下，如何判断迁移学习的效果？我们通过超过42,000次实验，在16个数据集上对比了23种迁移性度量方法。结果表明，现有方法整体表现不佳。但简单的k-NN评估（常用于自监督特征质量评价）不仅超越所有现有度量，还具备更高的计算效率和实现简便性。
原文摘要 · Abstract (English)
How well can one expect transfer learning to work in a new setting where the domain is shifted, the task is different, and the architecture changes? Many transfer learning metrics have been proposed to answer this question. But how accurate are their predictions in a realistic new setting? We conducted an extensive evaluation involving over 42,000 experiments comparing 23 transferability metrics across 16 different datasets to assess their ability to predict transfer performance. Our findings reveal that none of the existing metrics perform well across the board. However, we find that a simple k-nearest neighbor evaluation -- as is commonly used to evaluate feature quality for self-supervision -- not only surpasses existing metrics, but also offers better computational efficiency and ease of implementation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。