There are 5 repositories under ibm-research-ai topic.
A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
Interpretability and explainability of data and machine learning models
Regression Transformer (2023; Nature Machine Intelligence)
Knowledge-Aware RL agents with Commonsense Reasoning
Quality Controlled Paraphrase Generation (ACL 2022)
Codes for reproducing query-efficient black-box attacks in “AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks” , published at AAAI 2019
Codes for reproducing the contrastive explanation in “Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives”
Codes for reproducing the black-box adversarial attacks in “ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models,” ACM CCS Workshop on AI-Security, 2017
Codes for reproducing the robustness evaluation scores in “Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach,” ICLR 2018
Codes for reproducing the adversarial attacks on image captioning systems in “Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning,” ACL 2018
CROWN: A Neural Network Verification Framework for Networks with General Activation Functions
Semantic Search for Sustainable Development is experimental code for searching documents for text that "semantically" corresponds to any of the UN's Sustainable development goals/targets. For example, it can be used to mine the national development plan documents of a country and identify pieces of text that correspond to any of the SDGs in order to verify alignment of the plan with the SDGs.
Codes for reproducing the results of the paper "Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness" published at ICLR 2020
Source code for paper Choromanska et al. -- Beyond Backprop: Online Alternating Minimization with Auxiliary Variables -- http://proceedings.mlr.press/v97/choromanska19a.html
Codes for reproducing the white-box adversarial attacks in “EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples,” AAAI 2018
Code accompanying the paper Sobolev GAN https://arxiv.org/abs/1711.04894
Forecasting mixed migration for the Danish Refugee Council.
Codes for reproducing robustness-accuracy analysis in "Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models", ECCV 2018
Data for the ACL 2020 paper - Improving Segmentation for Technical Support Problems
A Testing Framework for Decision-Optimization Model Learning Algorithms
code repo associated to the ACL 2023 paper "DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications"
This repo includes code referenced in the paper A Rigorous Risk-aware Linear Approach to Extended Markov Ratio Decision Processes with Embedded Learning by Alexander Zadorojniy, Takayuki Osogami, and Orit Davidovich to appear in IJCAI 2023.
Planning tasks succinctly represent labeled transition systems, with each ground action corresponding to a label. This granularity, however, is not necessary for solving planning tasks and can be harmful, especially for model-free methods. In this work, we propose automatic approach to reduce the label sets for planning domains.