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
Tutorial for Decision Threshold In Machine Learning.

Decision-Threshold-ML Tutorial for improve skills: 'Decision Threshold In Machine Learning' (from GeeksforGeeks) by Marcus Mariano For more informatio

0 Jan 20, 2022
Examples and code for the Practical Machine Learning workshop series

Practical Machine Learning Workshop Series Practical Machine Learning for Quantitative Finance Post conference workshop at the WBS Spring Conference D

CompatibL 21 Jun 25, 2022
ArviZ is a Python package for exploratory analysis of Bayesian models

ArviZ (pronounced "AR-vees") is a Python package for exploratory analysis of Bayesian models. Includes functions for posterior analysis, data storage, model checking, comparison and diagnostics

ArviZ 1.3k Jan 05, 2023
Skforecast is a python library that eases using scikit-learn regressors as multi-step forecasters

Skforecast is a python library that eases using scikit-learn regressors as multi-step forecasters. It also works with any regressor compatible with the scikit-learn API (pipelines, CatBoost, LightGBM

Joaquín Amat Rodrigo 297 Jan 09, 2023
Fundamentals of Machine Learning

Fundamentals-of-Machine-Learning This repository introduces the basics of machine learning algorithms for preprocessing, regression and classification

Happy N. Monday 3 Feb 15, 2022
Deep Survival Machines - Fully Parametric Survival Regression

Package: dsm Python package dsm provides an API to train the Deep Survival Machines and associated models for problems in survival analysis. The under

Carnegie Mellon University Auton Lab 10 Dec 30, 2022
A machine learning model for Covid case prediction

CovidcasePrediction A machine learning model for Covid case prediction Problem Statement Using regression algorithms we can able to track the active c

VijayAadhithya2019rit 1 Feb 02, 2022
SynapseML - an open source library to simplify the creation of scalable machine learning pipelines

Synapse Machine Learning SynapseML (previously MMLSpark) is an open source library to simplify the creation of scalable machine learning pipelines. Sy

Microsoft 3.9k Dec 30, 2022
jaxfg - Factor graph-based nonlinear optimization library for JAX.

Factor graphs + nonlinear optimization in JAX

Brent Yi 134 Dec 21, 2022
Data Efficient Decision Making

Data Efficient Decision Making

Microsoft 197 Jan 06, 2023
Automated Machine Learning Pipeline with Feature Engineering and Hyper-Parameters Tuning

The mljar-supervised is an Automated Machine Learning Python package that works with tabular data. I

MLJAR 2.4k Jan 02, 2023
Getting Profit and Loss Make Easy From Binance

Getting Profit and Loss Make Easy From Binance I have been in Binance Automated Trading for some time and have generated a lot of transaction records,

17 Dec 21, 2022
Library for machine learning stacking generalization.

stacked_generalization Implemented machine learning *stacking technic[1]* as handy library in Python. Feature weighted linear stacking is also availab

114 Jul 19, 2022
Predicting diabetes over a five year period using logistic regression and the Pima First-Nation dataset

Diabetes This script uses the Pima First Nations dataset to create a model to predict whether or not an individual will develop Diabetes Mellitus Type

1 Mar 28, 2022
Machine Learning Model to predict the payment date of an invoice when it gets created in the system.

Payment-Date-Prediction Machine Learning Model to predict the payment date of an invoice when it gets created in the system.

15 Sep 09, 2022
2021 Machine Learning Security Evasion Competition

2021 Machine Learning Security Evasion Competition This repository contains code samples for the 2021 Machine Learning Security Evasion Competition. P

Fabrício Ceschin 8 May 01, 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
Evaluate on three different ML model for feature selection using Breast cancer data.

Anomaly-detection-Feature-Selection Evaluate on three different ML model for feature selection using Breast cancer data. ML models: SVM, KNN and MLP.

Tarek idrees 1 Mar 17, 2022
MLFlow in a Dockercontainer based on Azurite and Postgres

mlflow-azurite-postgres docker This is a MLFLow image which works with a postgres DB and a local Azure Blob Storage Instance (Azurite). This image is

2 May 29, 2022
Compare MLOps Platforms. Breakdowns of SageMaker, VertexAI, AzureML, Dataiku, Databricks, h2o, kubeflow, mlflow...

Compare MLOps Platforms. Breakdowns of SageMaker, VertexAI, AzureML, Dataiku, Databricks, h2o, kubeflow, mlflow...

Thoughtworks 318 Jan 02, 2023