期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 45, 期 1, 页码 841-851出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2022.3147798
关键词
PAC bayes; meta-lear ning; few-shot learning; transfer learning
We introduce a new PAC-Bayes meta-learning algorithm that solves few-shot learning by extending the framework to handle multiple tasks and samples. Our generative-based approach estimates task-specific model parameters more expressively, resulting in well-calibrated and accurate models. These models perform competitively on few-shot classification and regression benchmarks.
We introduce a new and rigorously-formulated PAC-Bayes meta-learning algorithm that solves few-shot learning. Our proposed method extends the PAC-Bayes framework from a single-task setting to the meta-learning multiple-task setting to upper-bound the error evaluated on any, even unseen, tasks and samples. We also propose a generative-based approach to estimate the posterior of task-specific model parameters more expressively compared to the usual assumption based on a multivariate normal distribution with a diagonal covariance matrix. We show that the models trained with our proposed meta-learning algorithm are well-calibrated and accurate, with state-of-the-art calibration errors while still being competitive on classification results on few-shot classification (mini-ImageNet and tiered-ImageNet) and regression (multi-modal task-distribution regression) benchmarks.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据