![](https://img-blog.csdnimg.cn/20201014180756754.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
元学习
文章平均质量分 59
_Blueblue_
ok fine
展开
-
【联邦/元学习】个性化联邦学习论文笔记:《Improving federated learning personalization via model agnostic meta learning》
论文:《Improving federated learning personalization via model agnostic meta learning》Citation:Y. Jiang, J. Konecny, K. Rush, and S. Kannan, “Improving federated learning personalization via model agnostic meta learning,” arXiv preprint arXiv:1909.12488, 201原创 2021-10-27 19:48:03 · 2321 阅读 · 3 评论 -
【元学习】MER代码实现:Task/Class-IL增量场景下的Meta-Experience Replay详解
论文《Learning to learn without forgetting by maximizing transfer and minimizing interference》中提出了“将经验重放与元学习相结合“的增量学习方法:Meta-Experience Replay (MER)。这里整理了一下MER的算法流程和代码实现。论文解析可以戳这里:论文解析:Learning to learn without forgetting by maximizing transfer and mi原创 2021-09-26 19:29:47 · 1824 阅读 · 1 评论 -
【元学习】iTAML论文精读:持续/增量学习下与任务无关的元学习模型
论文:J. Rajasegaran, S. Khan, M. Hayat, F. S. Khan, M. Shah, itaml: An incremental task-agnostic meta-learning approach, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 13588–13597.在CVPR2020上发表的一篇结合元学习和增量学习的原创 2021-09-14 14:20:00 · 867 阅读 · 4 评论 -
【联邦元学习】论文解读:Federated Meta-Learning for Fraudulent Credit Card Detection
论文:Zheng W, Yan L, Gou C, et al. Federated Meta-Learning for Fraudulent Credit Card Detection[C], Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence Special Track on AI in FinTech. Pages 4654-4660. 2020: 4654-4660.【原创 2021-09-03 16:36:36 · 705 阅读 · 1 评论 -
【联邦元学习】读懂Per-FedAvg个性化联邦学习:Personalized Federated Learning: A Meta-Learning Approach
论文:Fallah A, Mokhtari A, Ozdaglar A. Personalized Federated Learning: A Meta-Learning Approach[J]. arXiv pre-print server, 2020.这篇文章提出了FedAvg的变体——Per-FedAvg,旨在解决联邦学习中的个性化问题。在联邦学习中结合元学习模型MAML,试图找出一个全局模型,使之在每个节点针对其自身的损失函数进行更新后均表现良好。【原创,转载需标明出处】论文解析(内含论文原原创 2021-09-02 14:08:39 · 1876 阅读 · 1 评论 -
【联邦元学习】解读FedMeta框架:Federated Meta-Learning with Fast Convergence and Efficient Communication
论文:Chen F , Luo M , Dong Z , et al. Federated Meta-Learning with Fast Convergence and Efficient Communication[J]. arXiv, 2018.华为的一篇结合联邦学习和元学习的论文:在联邦框架下,基于MAML或Meta-SGD构建FedMeta模型。【原创,转载需标明出处】论文解析(内含论文原文、代码链接):https://ripe-heliotrope-6f4.notion.site/Fed原创 2021-09-01 14:04:02 · 1490 阅读 · 0 评论 -
【元学习】MER论文解析:持续/增量学习下的元学习模型
论文:M. Reimer, I. Cases, R. Ajemian, M. Liu, I. Rish, Y. Tu, G. Tesauro, Learning to learn without forgetting by maximizing transfer and minimizing interference, in: ICLR, 2019.提出了Meta-Experience Replay (MER) 模型,将经验重放与基于优化的元学习相结合,基于Reptile元学习模型,以最大限度地转移和.原创 2021-08-31 17:21:13 · 1117 阅读 · 0 评论