GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → Piyushi-0 → ACE

Piyushi-0 / ACE

Licence: other
Code for our paper, Neural Network Attributions: A Causal Perspective (ICML 2019).

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Labels

machine-learningdeep-learningneural-networkcausalityicmlattribution-methods

Projects that are alternatives of or similar to ACE

Pwc
Papers with code. Sorted by stars. Updated weekly.
Stars: ✭ 15,288 (+32427.66%)
Mutual labels:  icml
Awesome-Neural-Logic
Awesome Neural Logic and Causality: MLN, NLRL, NLM, etc. 因果推断，神经逻辑，强人工智能逻辑推理前沿领域。
Stars: ✭ 106 (+125.53%)
Mutual labels:  causality
Scribe-py
Regulatory networks with Direct Information in python
Stars: ✭ 28 (-40.43%)
Mutual labels:  causality
pycid
Library for graphical models of decision making, based on pgmpy and networkx
Stars: ✭ 64 (+36.17%)
Mutual labels:  causality
ENCO
Official repository of the paper "Efficient Neural Causal Discovery without Acyclicity Constraints"
Stars: ✭ 52 (+10.64%)
Mutual labels:  causality
iPerceive
Applying Common-Sense Reasoning to Multi-Modal Dense Video Captioning and Video Question Answering | Python3 | PyTorch | CNNs | Causality | Reasoning | LSTMs | Transformers | Multi-Head Self Attention | Published in IEEE Winter Conference on Applications of Computer Vision (WACV) 2021
Stars: ✭ 52 (+10.64%)
Mutual labels:  causality
TaLKConvolutions
Official PyTorch implementation of Time-aware Large Kernel (TaLK) Convolutions (ICML 2020)
Stars: ✭ 26 (-44.68%)
Mutual labels:  icml
cfml tools
My collection of causal inference algorithms built on top of accessible, simple, out-of-the-box ML methods, aimed at being explainable and useful in the business context
Stars: ✭ 24 (-48.94%)
Mutual labels:  causality
Generalization-Causality
关于domain generalization，domain adaptation，causality，robutness，prompt，optimization，generative model各式各样研究的阅读笔记
Stars: ✭ 482 (+925.53%)
Mutual labels:  causality
CREST
A Causal Relation Schema for Text
Stars: ✭ 19 (-59.57%)
Mutual labels:  causality
causeinfer
Machine learning based causal inference/uplift in Python
Stars: ✭ 45 (-4.26%)
Mutual labels:  causality
RECCON
This repository contains the dataset and the PyTorch implementations of the models from the paper Recognizing Emotion Cause in Conversations.
Stars: ✭ 126 (+168.09%)
Mutual labels:  causality
causal-learn
Causal Discovery for Python. Translation and extension of the Tetrad Java code.
Stars: ✭ 428 (+810.64%)
Mutual labels:  causality
cfvqa
[CVPR 2021] Counterfactual VQA: A Cause-Effect Look at Language Bias
Stars: ✭ 96 (+104.26%)
Mutual labels:  causality
causaldag
Python package for the creation, manipulation, and learning of Causal DAGs
Stars: ✭ 82 (+74.47%)
Mutual labels:  causality
rebias
Official Pytorch implementation of ReBias (Learning De-biased Representations with Biased Representations), ICML 2020
Stars: ✭ 125 (+165.96%)
Mutual labels:  icml
Causal Reading Group
We will keep updating the paper list about machine learning + causal theory. We also internally discuss related papers between NExT++ (NUS) and LDS (USTC) by week.
Stars: ✭ 339 (+621.28%)
Mutual labels:  causality
icml-nips-iclr-dataset
Papers, authors and author affiliations from ICML, NeurIPS and ICLR 2006-2021
Stars: ✭ 21 (-55.32%)
Mutual labels:  icml
Dowhy
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.
Stars: ✭ 3,480 (+7304.26%)
Mutual labels:  causality
Causal-Deconvolution-of-Networks
Causal Deconvolution of Networks by Algorithmic Generative Models
Stars: ✭ 25 (-46.81%)
Mutual labels:  causality
View All Similar Projects ➔

ACE

Neural Network Attributions: A Causal Perspective
Aditya Chattopadhyay, Piyushi Manupriya, Anirban Sarkar, Vineeth N Balasubramanian
Presented at ICML 2019

Dependencies:
scikit-learn (0.19.1)
scipy (0.17.0)
torch (0.4.0)
joblib (0.11)
matplotlib (1.5.1)
numpy (1.14.5)

Usage-
MNIST:
  sh run_mnist_mod.sh
  MNIST.ipynb
  
Iris:
  python decision_tree.py
  train.ipynb
  ACE.ipynb
  
Synthetic Dataset:
  toy_dataset.ipynb
  python evaluate_lstm.py
  
Aircraft:
  python lstm.py
  python find_tau.py
  python aircraft_causal_interventions.py foldername
  eg. python aircraft_causal_interventions.py "40"
  python learn_causal_regressors.py learn effect_num_header effect
  eg. python learn_causal_regressors.py learn 5 LATG
  python causal_analysis_final.py predict effect foldername start_time
  eg. python causal_analysis_final.py predict GS "40" 100

NASA dataset used in Aircraft code is uploaded at https://drive.google.com/open?id=1rEZ3veRpcKH5OZKAoXuVTyC9oMnn78ra
Class-conditional Beta VAE code used in MNIST experiments is adapted from Beta VAE code from https://github.com/1Konny/Beta-VAE

If you use this code, please cite our paper:
Aditya Chattopadhyay, Piyushi Manupriya, Anirban Sarkar, Vineeth N Balasubramanian. "Neural Network Attributions: A Causal Perspective", in International Conference on Machine Learning (ICML), 2019.
Bibtex
and consider giving a star to our repository.

References:
https://github.com/1Konny/Beta-VAE
https://c3.nasa.gov/dashlink/projects/85/resources/?type=ds

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].