Hanchen

hi, @hindupuravinash Thanks for you contribution to the community, I found this paper is high cited and impactful in areas of applying GANs for domain adaptation tasks :) http://openaccess.thecvf.com/content_cvpr_2017/html/Bousmalis_Unsupervised_Pixel-Level_Domain_CVPR_2017_paper.html

hi, @Cartucho thanks for you contribution, it do help me a lot with understanding the criteria metric of PASCOL VOC 2012! I have a similar question to #93 but not...

change the storage into 64 bits, since sometimes it encounter the overflow multiplication

2

also see here #136

13.4 数学符号/公式没有正常显示

3

https://openmlsys.github.io/chapter_federated_learning/privacy_encryption_algorithm.html 在网页上和我本地build的html都遇到了数学符号/公式没有正常显示的问题。@chengtianwu @eedalong

[拓展章节] Graph + MLSys

6

与@luomai 老师交流后，我很希望能够Co-Lead/参与到这一拓展章节的撰写过程中，我对Graph, GNN等比较熟悉，刚开始了解MLSys + Graph这一有趣的方向。

[内容补充与拓展]联邦学习系统

4

可否share一下所有图表的原始文件？ 13.1 - [x] 简单语句的修改、增加Flower的介绍 - [x] 联邦迁移学习的Clarification，放到展望里来写 13.2 - [x] FedAvg存在的问题, e.g., [SCAFFOLD, ICML 2020](https://arxiv.org/abs/1910.06378)和一些改进的方法, e.g., [FEDBE, ICLR 2021](https://openreview.net/pdf?id=dgtpE6gKjHn) 13.4 - [ ] 一些公式格式问题的修改 - [ ] DP存在的问题以及可改进的空间e.g., Ryan...

Jupyter Notebook vs Python/PyCharm

3

Hi, there. I am following the tutorial [here](https://scanpy-tutorials.readthedocs.io/en/latest/pbmc3k.html), it works perfectly with Jupyter Notebook, but I do encounter the following errors when running the code in command line or PyCharm....

What Makes a Good Pre-Training on Points Cloud?

1

**General Interpretability:** - [interpretable ml book](https://christophm.github.io/interpretable-ml-book/shapley.html), specifically sections on `learned features`, `Shapley values`, `Influential Instance` - "Network dissection: Quantifying interpretability of deep visual representations", CVPR 2017 - "Feature Visualisation", Olah,...

Update on Literatures

4

**Point Cloud Completion** - "Topnet: Structural point cloud decoder", CVPR 2019 - "3D Shape Completion with Multi-view Consistent Inference", AAAI 2020 - "Morphing and Sampling Network for Dense Point Cloud...

Basically in consistent with the updated iccv submission version: 1. Few-shot learning 2. Network dissection and adjusted mutual information 3. Object-Level Contrastive Learning 4. Readme and website