【论文笔记】多任务学习（Multi-Task Learning）
1. 前言 多任务学习（Multi-task learning）是和单任务学习（single-task learning）相对的一种机器学习方法。在机器学习领域，标准的算法理论是一次学习一个任务，也就是系统的输出为实数的情况。复杂的学习问题先被分解成理论上独立的子问题，然后分别对每个子问题 ...
原文：论文笔记(1)—"Clustered federated learning: Model-Agnostic distributed multi-Task optimization under privacy constraints"
Motivation In this paper , authors presented a novel group based federated learning to solve incongruent data problem. In traditional FL methods, like FedAvg, assumes all clients data coming from the ...
2021-01-15 22:00 0 363 推荐指数：
相关推荐
论文笔记：Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks ICML 2017 Paper：https://arxiv.org/pdf/1703.03400.pdf Code for the regression ...
论文笔记之：Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach
Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach 2017.11.28 Introduction： 人脸属性的识别在社会交互，提供了非常广泛的信息，包括 ...
SegFix: Model-Agnostic Boundary Refinement for Segmentation(ECCV2020)论文笔记
1 问题描述 本文提出了一种模型无关的后处理方案，即用内部像素的预测代替原来不可靠的边界像素预测，以提高由任何现有分割模型生成的分割结果的边界质量。该方法仅对输入图像进行两步处理：(i)定位边界像素 ...
论文阅读 | A Survey on Multi-Task Learning
摘要 多任务学习(Multi-Task Learning, MTL)是机器学习中的一种学习范式，其目的是利用包含在多个相关任务中的有用信息来帮助提高所有任务的泛化性能。 首先，我们将不同的MTL算法分为特征学习法、低秩方法、任务聚类方法、任务关系学习方法和分解方法，然后讨论每种方法的特点 ...
论文笔记(2)—"Adaptive Federated Optimization"
Intuition Authors demonstrated that the gap between centralized and federated performance was caused by two reasons: 1)client drift, 2) a lack ...
论文笔记之：Instance-aware Semantic Segmentation via Multi-task Network Cascades
Instance-aware Semantic Segmentation via Multi-task Network Cascades Jifeng Dai Kaiming He Jian Sun 本文的出发点是做Instance-aware Semantic ...
【论文笔记】A survey on federated learning（综述）
Federated learning; Privacy protection; Machine learni ...