Algorithms for explaining machine learning models
counterfactual 开源项目推荐(132 个)
counterfactual 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 132 个仓库Must-read papers and resources related to causal inference and machine (deep) learning
CausalLift: Python package for causality-based Uplift Modeling in real-world business
对解释的对抗攻击及如何防御
CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
A Python package for causal inference using Synthetic Controls
Home for all packages related to the Counterfactual project
[CVPR 2021] Counterfactual VQA: A Cause-Effect Look at Language Bias
The repository contains lists of papers on causality and how relevant techniques are being used to further enhance deep learning era computer vision solutions.
Counterfactual Samples Synthesizing for Robust VQA
(ICML 2023) High Fidelity Image Counterfactuals with Probabilistic Causal Models
FairPut - 基于LightGBM的机器学习公平性框架——可解释性、稳健性、公平性(@firmai)
📄 Counterfactual: Generalized State Channels Paper
MixEth: efficient, trustless coin mixing service for Ethereum
Materials Collection for Causal Inference
Machine learning research code for causal perception: comparing competing structural causal models (SCMs) via interventional and counterfactual distributions, applied to fair credit decisions. Open source by Santander AI Lab.
Code for the paper "Getting a CLUE: A Method for Explaining Uncertainty Estimates"
Counterfactual Reasoning VQA Dataset
[ML4H 2022] This is the code for our paper `Counterfactual and Factual Reasoning over Hypergraphs for Interpretable Clinical Predictions on EHR'.
PyTorch implementation for our proposed CFIE in EMNLP 2021 paper "Uncovering Main Causalities for Long-tailed Information Extraction".
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/counterfactual。
- 该话题在 GitHub 上共有 132 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 5557 Star,覆盖 5 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。