counterfactual

952 papers with code • 0 benchmarks • 0 datasets

This task has no description! Would you like to contribute one?

Libraries

Use these libraries to find counterfactual models and implementations

Most implemented papers

Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations

microsoft/DiCE 19 May 2019

Post-hoc explanations of machine learning models are crucial for people to understand and act on algorithmic predictions.

Counterfactual Multi-Agent Policy Gradients

opendilab/DI-engine 24 May 2017

COMA uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents' policies.

Unbiased Scene Graph Generation from Biased Training

KaihuaTang/Scene-Graph-Benchmark.pytorch CVPR 2020

Today's scene graph generation (SGG) task is still far from practical, mainly due to the severe training bias, e. g., collapsing diverse "human walk on / sit on / lay on beach" into "human on beach".

Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR

microsoft/DiCE 1 Nov 2017

We suggest data controllers should offer a particular type of explanation, unconditional counterfactual explanations, to support these three aims.

Solving Imperfect-Information Games via Discounted Regret Minimization

b-inary/wasm-postflop 11 Sep 2018

Counterfactual regret minimization (CFR) is a family of iterative algorithms that are the most popular and, in practice, fastest approach to approximately solving large imperfect-information games.

Deep Counterfactual Regret Minimization

deepmind/open_spiel 1 Nov 2018

This paper introduces Deep Counterfactual Regret Minimization, a form of CFR that obviates the need for abstraction by instead using deep neural networks to approximate the behavior of CFR in the full game.

Single Deep Counterfactual Regret Minimization

EricSteinberger/Deep-CFR 22 Jan 2019

Counterfactual Regret Minimization (CFR) is the most successful algorithm for finding approximate Nash equilibria in imperfect information games.

CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms

indyfree/CARLA 2 Aug 2021

In summary, our work provides the following contributions: (i) an extensive benchmark of 11 popular counterfactual explanation methods, (ii) a benchmarking framework for research on future counterfactual explanation methods, and (iii) a standardized set of integrated evaluation measures and data sets for transparent and extensive comparisons of these methods.

An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models

mcgill-nlp/bias-bench ACL 2022

Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on.

Locating and Editing Factual Associations in GPT

kmeng01/rome 10 Feb 2022

To test our hypothesis that these computations correspond to factual association recall, we modify feed-forward weights to update specific factual associations using Rank-One Model Editing (ROME).