随笔分类 - 论文阅读笔记
搜索推荐论文速读2
摘要：1. A Model-Agnostic Causal Learning Framework for Recommendation using Search Data. WWW 2022 从因果分析的角度看，用于表示特征的embedding向量与用户的点击反馈有着复杂的关系。作者认为，这种复杂的关系可
推荐搜索算法论文速读1
摘要：# n-gram 模型 参考：https://zhuanlan.zhihu.com/p/32829048 简介：一个句子或者一个联想词语，可以使用链式规则建模，利用马尔科夫链的假设（当前词语的产生只与前n个词语产生的概率相关）。n-gram中的n指的就是马尔科夫链假设中的长度。 定义：一元模型uni
【论文阅读笔记】Distiling Causal Effect of Data in Class-Incremental Learning
摘要：Author: Hanwang Zhang, Xinting Hu Create_time: April 24, 2022 11:01 AM Edited_by: Huang Yujun Publisher: CVPR 2021 Org: Nanyang Technological Universi
【论文阅读笔记】Learning to Prompt for Continual Learning
摘要：Create_time: April 27, 2022 5:21 PM Edited_by: Huang Yujun Org: Google Research, Northeastern University Learning to Prompt for Continual Learning [38
【论文阅读笔记】iCaRL: Incremental Classifier and Representation Learning
摘要：Author: Alexander Kolesnikov Key_words: nearest-mean-of-exemplar rule, prioritized exampler selection,representation learning Create_time: September 1
【论文阅读笔记】Class-Incremental Learning with Strong Pre-trained Models
摘要：Key_words: Continual learning, strong pretrained model, fix, fusion Create_time: April 14, 2022 6:32 PM Edited_by: Huang Yujun Publisher: CVPR 2022 Sc
