EEML-2021

Blogs

• https://michaelnielsen.org/
• https://www.inference.vc/about/
• https://deepmind.com/blog

Papers

Mitigating Unwanted Biases with Adversarial Learning (presented @ Journal Club - Fairness):

• paper: https://dl.acm.org/doi/pdf/10.1145/3278721.3278779
• implementation notebook: https://colab.research.google.com/notebooks/ml_fairness/adversarial_debiasing.ipynb#scrollTo=-Ei_ioWT_DDa

Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings.

• https://papers.nips.cc/paper/2016/file/a486cd07e4ac3d270571622f4f316ec5-Paper.pdf

Modelling tabular data using conditional GAN

• paper: https://papers.nips.cc/paper/2019/file/254ed7d2de3b23ab10936522dd547b78-Paper.pdf
• implementation: https://sdv.dev/CTGAN/ , https://github.com/sdv-dev/CTGAN

Robust Membership Encoding: Inference Attacks and Copyright Protection for Deep Learning

• https://arxiv.org/abs/1909.12982

Topics to explore

• Transformers
• Self-supervised learning
• Contrastive learning
• Graph nets
  • tutorial: https://colab.research.google.com/github/eemlcommunity/PracticalSessions2021/blob/main/graphnets/graphnets_tutorial.ipynb
  • Adversarial attack on graph nets
  • • https://github.com/safe-graph/graph-adversarial-learning-literature
  • • https://github.com/DSE-MSU/DeepRobust

Useful tools and links:

• Connected papers: https://www.connectedpapers.com/
• Arxiv Sanity: http://www.arxiv-sanity.com/
• How to read a paper: http://ccr.sigcomm.org/online/files/p83-keshavA.pdf
• More about paper reading: https://www.cs.princeton.edu/courses/archive/fall19/cos418/518_paper_prep.txt
• Literature visualisation: https://www.litmaps.co/