Code implementing "Improving Deep Learning Interpretability by Saliency Guided Training"

Overview

Saliency Guided Training

Code implementing "Improving Deep Learning Interpretability by Saliency Guided Training" by Aya Abdelsalam Ismail, Hector Corrada Bravo*, Soheil Feizi*.

alt text

Overview

Saliency methods have been widely used to highlight important input features in model predictions. Most existing methods use backpropagation on a modified gradient function to generate saliency maps. Thus, noisy gradients can result in unfaithful feature attributions. In this paper, we tackle this issue and introduce a saliency guided training† procedure for neural networks to reduce noisy gradients used in predictions while retaining the predictive performance of the model. Our saliency guided training procedure iteratively masks features with small and potentially noisy gradients while maximizing the similarity of model outputs for both masked and unmasked inputs. We apply the saliency guided training procedure to various synthetic and real data sets from computer vision, natural language processing, and time series across diverse neural architectures, including Recurrent Neural Networks, Convolutional Networks, and Transformers. Through qualitative and quantitative evaluations, we show that saliency guided training procedure significantly improves model interpretability across various domains while preserving its predictive performance.

Usage:

  • Create the following folder structure.
Scripts
    │
    ├── data
    ├── models
    └── outputs 
      ├── SaliencyValues
      ├── MaskedAcc
      └──Graphs
  • To run experiment cd Scripts

For MNIST Regular Training

  • For MNIST Experiments run regular training: python train_MNIST.py
  • To get accuracy drop run: python maskedAcc_MNIST.py

For MNIST Interpretable Training

  • Add interpretable training flags, here 50% of the features are masked during training with a random.
    python train_MNIST.py --trainingType interpretable --featuresDroped 0.5 --RandomMasking
  • To get accuracy drop run with the same flags used in training:
    python maskedAcc_MNIST.py --trainingType interpretable --featuresDroped 0.5 --RandomMasking
FOSS Digital Asset Distribution Platform built on Frappe.

Digistore FOSS Digital Assets Marketplace. Distribute digital assets, like a pro. Video Demo Here Features Create, attach and list digital assets (PDF

Mohammad Hussain Nagaria 30 Dec 08, 2022
Code for testing convergence rates of Lipschitz learning on graphs

📈 LipschitzLearningRates The code in this repository reproduces the experimental results on convergence rates for k-nearest neighbor graph infinity L

2 Dec 20, 2021
Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

Semantic Segmentation on MIT ADE20K dataset in PyTorch This is a PyTorch implementation of semantic segmentation models on MIT ADE20K scene parsing da

MIT CSAIL Computer Vision 4.5k Jan 08, 2023
The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalization".

Codebase for learning control flow in transformers The official repository for our paper "The Neural Data Router: Adaptive Control Flow in Transformer

Csordás Róbert 24 Oct 15, 2022
PyTorch framework, for reproducing experiments from the paper Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks

Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks. Code, based on the PyTorch framework, for reprodu

Asaf 3 Dec 27, 2022
QRec: A Python Framework for quick implementation of recommender systems (TensorFlow Based)

Introduction QRec is a Python framework for recommender systems (Supported by Python 3.7.4 and Tensorflow 1.14+) in which a number of influential and

Yu 1.4k Jan 01, 2023
Sematic-Segmantation - Semantic Segmentation on MIT ADE20K dataset in PyTorch

Semantic Segmentation on MIT ADE20K dataset in PyTorch This is a PyTorch impleme

Berat Eren Terzioğlu 4 Mar 22, 2022
A pytorch implementation of MBNET: MOS PREDICTION FOR SYNTHESIZED SPEECH WITH MEAN-BIAS NETWORK

Pytorch-MBNet A pytorch implementation of MBNET: MOS PREDICTION FOR SYNTHESIZED SPEECH WITH MEAN-BIAS NETWORK Training To train a new model, please ru

46 Dec 28, 2022
An open-source online reverse dictionary.

An open-source online reverse dictionary.

THUNLP 6.3k Jan 09, 2023
The official implementation of CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing

CSGStumpNet The official implementation of CSG-Stump: A Learning Friendly CSG-Like Representation for Interpretable Shape Parsing Paper | Project page

Daxuan 39 Dec 26, 2022
Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition - NeurIPS2021

Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition Project Page | Video | Paper Implementation for Neural-PIL. A novel method wh

Computergraphics (University of Tübingen) 64 Dec 29, 2022
Neural Architecture Search Powered by Swarm Intelligence 🐜

Neural Architecture Search Powered by Swarm Intelligence 🐜 DeepSwarm DeepSwarm is an open-source library which uses Ant Colony Optimization to tackle

288 Oct 28, 2022
[ICML 2021] A fast algorithm for fitting robust decision trees.

GROOT: Growing Robust Trees Growing Robust Trees (GROOT) is an algorithm that fits binary classification decision trees such that they are robust agai

Cyber Analytics Lab 17 Nov 21, 2022
Neural Dynamic Policies for End-to-End Sensorimotor Learning

This is a PyTorch based implementation for our NeurIPS 2020 paper on Neural Dynamic Policies for end-to-end sensorimotor learning.

Shikhar Bahl 47 Dec 11, 2022
The code of “Similarity Reasoning and Filtration for Image-Text Matching” [AAAI2021]

SGRAF PyTorch implementation for AAAI2021 paper of “Similarity Reasoning and Filtration for Image-Text Matching”. It is built on top of the SCAN and C

Ronnie_IIAU 149 Dec 22, 2022
Source code for paper "Deep Diffusion Models for Robust Channel Estimation", TBA.

diffusion-channels Source code for paper "Deep Diffusion Models for Robust Channel Estimation". Generic flow: Use 'matlab/main.mat' to generate traini

The University of Texas Computational Sensing and Imaging Lab 15 Dec 22, 2022
OpenIPDM is a MATLAB open-source platform that stands for infrastructures probabilistic deterioration model

Open-Source Toolbox for Infrastructures Probabilistic Deterioration Modelling OpenIPDM is a MATLAB open-source platform that stands for infrastructure

CIVML 0 Jan 20, 2022
This thesis is mainly concerned with state-space methods for a class of deep Gaussian process (DGP) regression problems

Doctoral dissertation of Zheng Zhao This thesis is mainly concerned with state-space methods for a class of deep Gaussian process (DGP) regression pro

Zheng Zhao 21 Nov 14, 2022
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

We challenge a common assumption underlying most supervised deep learning: that a model makes a prediction depending only on its parameters and the features of a single input. To this end, we introdu

OATML 360 Dec 28, 2022
This is an example implementation of the paper "Cross Domain Robot Imitation with Invariant Representation".

IR-GAIL This is an example implementation of the paper "Cross Domain Robot Imitation with Invariant Representation". Dependency The experiments are de

Zhao-Heng Yin 1 Jul 14, 2022