An implementation of Relaxed Linear Adversarial Concept Erasure (RLACE)

Related tags

Machine LearningRLACE
Overview

Background

This repository contains an implementation of Relaxed Linear Adversarial Concept Erasure (RLACE). Given a dataset X of dense representations and labels y for some concept (e.g. gender), the method identifies a rank-k subsapce whose neutralization (suing an othogonal projection matrix) prevents linear classifiers from recovering the concept from the representations.

The method relies on a relaxed and constrained version of a minimax game between a predictor that aims to predict y and a projection matrix P that is optimized to prevent the prediction.

How to run

A simple running example is provided within rlace.py.

Parameters

The main method, solve_adv_game, receives several arguments, among them:

  • rank: the rank of the neutralized subspace. rank=1 is emperically enough to prevent linear prediction in binary classification problem.

  • epsilon: stopping criterion for the adversarial game. Stops if abs(acc - majority_acc) < epsilon.

  • optimizer_class: torch.optim optimizer

  • optimizer_params_predictor / optimizer_params_P: parameters for the optimziers of the predictor and the projection matrix, respectively.

Running example:

num_iters = 50000
rank=1
optimizer_class = torch.optim.SGD
optimizer_params_P = {"lr": 0.003, "weight_decay": 1e-4}
optimizer_params_predictor = {"lr": 0.003,"weight_decay": 1e-4}
epsilon = 0.001 # stop 0.1% from majority acc
batch_size = 256

output = solve_adv_game(X_train, y_train, X_dev, y_dev, rank=rank, device="cpu", out_iters=num_iters, optimizer_class=optimizer_class, optimizer_params_P =optimizer_params_P, optimizer_params_predictor=optimizer_params_predictor, epsilon=epsilon,batch_size=batch_size)

Optimization: Even though we run a concave-convex minimax game, which is generallly "well-behaved", optimziation with alternate SGD is still not completely straightforward, and may require some tuning of the optimizers. Accuracy is also not expected to monotonously decrease in optimization; we return the projection matrix which performed best along the entire game. In all experiments on binary classification problems, we identified a projection matrix that neutralizes a rank-1 subspace and decreases classification accuracy to near-random (50%).

Using the projection:

output that is returned from solve_adv_game is a dictionary, that contains the following keys:

  1. score: final accuracy of the predictor on the projected data.

  2. P_before_svd: the final approximate projection matrix, before SVD that guarantees it's a proper orthogonal projection matrix.

  3. P: a proper orthogonal matrix that neutralizes a rank-k subspace.

The ``clean" vectors are given by X.dot(output["P"]).

Owner
Shauli Ravfogel
Graduate student, BIU NLP lab
Shauli Ravfogel
AP1 Transcription Factor Binding Site Prediction

A machine learning project that predicted binding sites of AP1 transcription factor, using ChIP-Seq data and local DNA shape information.

1 Jan 21, 2022
Case studies with Bayesian methods

Case studies with Bayesian methods

Baze Petrushev 8 Nov 26, 2022
Python 3.6+ toolbox for submitting jobs to Slurm

Submit it! What is submitit? Submitit is a lightweight tool for submitting Python functions for computation within a Slurm cluster. It basically wraps

Facebook Incubator 768 Jan 03, 2023
Dual Adaptive Sampling for Machine Learning Interatomic potential.

DAS Dual Adaptive Sampling for Machine Learning Interatomic potential. How to cite If you use this code in your research, please cite this using: Hong

6 Jul 06, 2022
A Collection of Conference & School Notes in Machine Learning πŸ¦„πŸ“πŸŽ‰

Machine Learning Conference & Summer School Notes. πŸ¦„πŸ“πŸŽ‰

558 Dec 28, 2022
Flightfare-Prediction - It is a Flightfare Prediction Web Application Using Machine learning,Python and flask

Flight_fare-Prediction It is a Flight_fare Prediction Web Application Using Machine learning,Python and flask Using Machine leaning i have created a F

1 Dec 06, 2022
A Microsoft Azure Web App project named Covid 19 Predictor using Machine learning Model

A Microsoft Azure Web App project named Covid 19 Predictor using Machine learning Model (Random Forest Classifier Model ) that helps the user to identify whether someone is showing positive Covid sym

Priyansh Sharma 2 Oct 06, 2022
A concept I came up which ditches the idea of "layers" in a neural network.

Dynet A concept I came up which ditches the idea of "layers" in a neural network. Install Copy Dynet.py to your project. Run the example Install matpl

Anik Patel 4 Dec 05, 2021
GroundSeg Clustering Optimized Kdtree

ground seg and clustering based on kitti velodyne data, and a additional optimized kdtree for knn and radius nn search

2 Dec 02, 2021
Metric learning algorithms in Python

metric-learn: Metric Learning in Python metric-learn contains efficient Python implementations of several popular supervised and weakly-supervised met

1.3k Dec 28, 2022
CyLP is a Python interface to COIN-OR’s Linear and mixed-integer program solvers (CLP, CBC, and CGL)

CyLP CyLP is a Python interface to COIN-OR’s Linear and mixed-integer program solvers (CLP, CBC, and CGL). CyLP’s unique feature is that you can use i

COIN-OR Foundation 161 Dec 14, 2022
Tools for Optuna, MLflow and the integration of both.

HPOflow - Sphinx DOC Tools for Optuna, MLflow and the integration of both. Detailed documentation with examples can be found here: Sphinx DOC Table of

Telekom Open Source Software 17 Nov 20, 2022
30 Days Of Machine Learning Using Pytorch

Objective of the repository is to learn and build machine learning models using Pytorch. 30DaysofML Using Pytorch

Mayur 119 Nov 24, 2022
A Python library for choreographing your machine learning research.

A Python library for choreographing your machine learning research.

AI2 270 Jan 06, 2023
Decision Tree Regression algorithm implemented on Python from scratch.

Decision_Tree_Regression I implemented the decision tree regression algorithm on Python. Unlike regular linear regression, this algorithm is used when

1 Dec 22, 2021
Tools for diffing and merging of Jupyter notebooks.

nbdime provides tools for diffing and merging of Jupyter Notebooks.

Project Jupyter 2.3k Jan 03, 2023
Book Recommender System Using Sci-kit learn N-neighbours

Model-Based-Recommender-Engine I created a book Recommender System using Sci-kit learn's N-neighbours algorithm for my model and the streamlit library

1 Jan 13, 2022
Home repository for the Regularized Greedy Forest (RGF) library. It includes original implementation from the paper and multithreaded one written in C++, along with various language-specific wrappers.

Regularized Greedy Forest Regularized Greedy Forest (RGF) is a tree ensemble machine learning method described in this paper. RGF can deliver better r

RGF-team 363 Dec 14, 2022
Project to deploy a machine learning model based on Titanic dataset from Kaggle

kaggle_titanic_deploy Project to deploy a machine learning model based on Titanic dataset from Kaggle In this project we used the Titanic dataset from

Vivian Yamassaki 8 May 23, 2022
UpliftML: A Python Package for Scalable Uplift Modeling

UpliftML is a Python package for scalable unconstrained and constrained uplift modeling from experimental data. To accommodate working with big data, the package uses PySpark and H2O models as base l

Booking.com 254 Dec 31, 2022