Instance-wise Feature Importance in Time (FIT)

Overview

Instance-wise Feature Importance in Time (FIT)

FIT is a framework for explaining time series perdiction models, by assigning feature importance to every observation over time. paper

To run the experiments, you need a trained prediction model that takes in time series data as input, and generates a prediction over time. You also need the training data to train the FIT generator. Below are the instruction for replicating experiments in the paper.

Data preparation

Two different simulated datasets are used in the experiments. The process of creating the data is explained below.

Simulated dataset (State data):

Run the following script to create the data and the ground thruth explanations for the state experiment. You can choose the total number of samples in the dataset as well as the lenght of each recording. The defaults are set to 1000 samples of length 100.

python3 data_generator/state_data.py --signal_len LENGTH_OF_SIGNALS --signal_num TOTAL_NUMBER_OF_SAMPLES

Simulated dataset (Spike data):

python3 data_generator/simulations_threshold_spikes.py 

MIMIC ICU dataset:

You need to have the MIMICIII database running on a server. Run the following scripts to query and preprocess the ICU mortality data (This step might take a few hours)

python3 data_generator/icu_mortality.py --sqluser YOUR_USER --sqlpass YOUR_PASSWORD

Run the following scripts to query and preprocess the ICU mortality data (This step might take a few hours)

python3 data_generator/icu_mortality.py ---sqluser YOUR_USER --sqlpass YOUR_PASSWORD

Running the importance assignment baselines

For running the experiments, you need to train: 1) The black-box predictor model and 2) the conditional generator. You can do this by passing the --train argument. If a model and conditional generator is already trained, skip the '--train' argument. To generate explanations for test samples using any of the baselines and for your required dataset (simulation, simulation_spike, mimic), run the following module.

python3 -m evaluation.baselines --data DATASET_NAME --explainer EXPLAINER_MODEL --train

In addition to FIT, you can also run experiments on different baseline explainers such as retain, deep lift, feature occlusion, etc.

Owner
Sana
Sana
OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)

OCTIS : Optimizing and Comparing Topic Models is Simple! OCTIS (Optimizing and Comparing Topic models Is Simple) aims at training, analyzing and compa

MIND 478 Jan 01, 2023
EqGAN - Improving GAN Equilibrium by Raising Spatial Awareness

EqGAN - Improving GAN Equilibrium by Raising Spatial Awareness Improving GAN Equilibrium by Raising Spatial Awareness Jianyuan Wang, Ceyuan Yang, Ying

GenForce: May Generative Force Be with You 149 Dec 19, 2022
CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

CALVIN CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks Oier Mees, Lukas Hermann, Erick Rosete,

Oier Mees 107 Dec 26, 2022
This is an open source library implementing hyperbox-based machine learning algorithms

hyperbox-brain is a Python open source toolbox implementing hyperbox-based machine learning algorithms built on top of scikit-learn and is distributed

Complex Adaptive Systems (CAS) Lab - University of Technology Sydney 21 Dec 14, 2022
CrossMLP - The repository offers the official implementation of our BMVC 2021 paper (oral) in PyTorch.

CrossMLP Cascaded Cross MLP-Mixer GANs for Cross-View Image Translation Bin Ren1, Hao Tang2, Nicu Sebe1. 1University of Trento, Italy, 2ETH, Switzerla

Bingoren 16 Jul 27, 2022
SCI-AIDE : High-fidelity Few-shot Histopathology Image Synthesis for Rare Cancer Diagnosis

SCI-AIDE : High-fidelity Few-shot Histopathology Image Synthesis for Rare Cancer Diagnosis Pretrained Models In this work, we created synthetic tissue

Emirhan Kurtuluş 1 Feb 07, 2022
Simultaneous NMT/MMT framework in PyTorch

This repository includes the codes, the experiment configurations and the scripts to prepare/download data for the Simultaneous Machine Translation wi

<a href=[email protected]"> 37 Sep 29, 2022
State of the art Semantic Sentence Embeddings

Contrastive Tension State of the art Semantic Sentence Embeddings Published Paper · Huggingface Models · Report Bug Overview This is the official code

Fredrik Carlsson 88 Dec 30, 2022
NIMA: Neural IMage Assessment

PyTorch NIMA: Neural IMage Assessment PyTorch implementation of Neural IMage Assessment by Hossein Talebi and Peyman Milanfar. You can learn more from

Kyryl Truskovskyi 293 Dec 30, 2022
Mae segmentation - Reproduction of semantic segmentation using masked autoencoder (mae)

ADE20k Semantic segmentation with MAE Getting started Install the mmsegmentation

97 Dec 17, 2022
Array Camera Ptychography

Array Camera Ptychography This repository provides the code for the following papers: Schulz, Timothy J., David J. Brady, and Chengyu Wang. "Photon-li

Brady lab in Optical Sciences 1 Nov 15, 2021
TrackFormer: Multi-Object Tracking with Transformers

TrackFormer: Multi-Object Tracking with Transformers This repository provides the official implementation of the TrackFormer: Multi-Object Tracking wi

Tim Meinhardt 321 Dec 29, 2022
TF Image Segmentation: Image Segmentation framework

TF Image Segmentation: Image Segmentation framework The aim of the TF Image Segmentation framework is to provide/provide a simplified way for: Convert

Daniil Pakhomov 546 Dec 17, 2022
Using pytorch to implement unet network for liver image segmentation.

Using pytorch to implement unet network for liver image segmentation.

zxq 1 Dec 17, 2021
High frequency AI based algorithmic trading module.

Flow Flow is a high frequency algorithmic trading module that uses machine learning to self regulate and self optimize for maximum return. The current

59 Dec 14, 2022
Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization

Towards Ultra-Resolution Neural Style Transfer via Thumbnail Instance Normalization Official PyTorch implementation for our URST (Ultra-Resolution Sty

czczup 148 Dec 27, 2022
ETMO: Evolutionary Transfer Multiobjective Optimization

ETMO: Evolutionary Transfer Multiobjective Optimization To promote the research on ETMO, benchmark problems are of great importance to ETMO algorithm

Songbai Liu 0 Mar 16, 2021
Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"

This repository contains code for the following two papers: VisualBERT: A Simple and Performant Baseline for Vision and Language (arxiv) with a short

Natural Language Processing @UCLA 463 Dec 09, 2022
Image-Scaling Attacks and Defenses

Image-Scaling Attacks & Defenses This repository belongs to our publication: Erwin Quiring, David Klein, Daniel Arp, Martin Johns and Konrad Rieck. Ad

Erwin Quiring 163 Nov 21, 2022
An open-source project for applying deep learning to medical scenarios

Auto Vaidya An open source solution for creating end-end web app for employing the power of deep learning in various clinical scenarios like implant d

Smaranjit Ghose 18 May 29, 2022