linktopast1900 Goto Github PK

attattr

best_ai_papers_2021

A curated list of the latest breakthroughs in AI by release date with a clear video explanation, link to a more in-depth article, and code. [work in progress]

cartography

Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics

compexp

Compositional Explanations of Neurons, NeurIPS 2020 https://arxiv.org/abs/2006.14032

iba-paper-code

Code for the Paper "Restricting the Flow: Information Bottlenecks for Attribution"

icml21_oaxe

imbalanced-semi-self

[NeurIPS 2020] Semi-Supervision (Unlabeled Data) & Self-Supervision Improve Class-Imbalanced / Long-Tailed Learning

private-transformers

make differentially private training of transformers easy

pytorch-multi-class-focal-loss

sdclr

[ICML 2021] “ Self-Damaging Contrastive Learning”, Ziyu Jiang, Tianlong Chen, Bobak Mortazavi, Zhangyang Wang

simcse

SimCSE: Simple Contrastive Learning of Sentence Embeddings

simplex

This repository contains the implementation of SimplEx, a method to explain the latent representations of black-box models with the help of a corpus of examples. For more details, please read our NeurIPS 2021 paper: 'Explaining Latent Representations with a Corpus of Examples'.

the-story-of-heads

This is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned" and the ACL 2021 paper "Analyzing Source and Target Contributions to NMT Predictions".

tracin

Implementation of Estimating Training Data Influence by Tracing Gradient Descent (NeurIPS 2020)

understanding-curricula

vqa-outliers

Code and Experiments for ACL-IJCNLP 2021 Paper "Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering."