activity
20222025
most citedInformation-Theoretic Bounds on The Removal of Attribute-Specific Bias From Neural Networks

1 citations · 2 across the 10 of their papers we have counts for

collaborators

10 papers

cs.LG2025

A Critical Review of Predominant Bias in Neural Networks

Jiazhi Li, Mahyar Khayatkhoei, Jiageng Zhu +3

Bias issues of neural networks garner significant attention along with its promising advancement. Among various bias issues, mitigating two predominant biases is crucial in advanci…

cs.CV2024

Look, Learn and Leverage (L): Mitigating Visual-Domain Shift and Discovering Intrinsic Relations via Symbolic Alignment

Hanchen Xie, Jiageng Zhu, Mahyar Khayatkhoei +2

Modern deep learning models have demonstrated outstanding performance on discovering the underlying mechanisms when both visual appearance and intrinsic relations (e.g., causal str…

cs.CV2024

An Investigation on The Position Encoding in Vision-Based Dynamics Prediction

Jiageng Zhu, Hanchen Xie, Jiazhi Li +2

Despite the success of vision-based dynamics prediction models, which predict object states by utilizing RGB images and simple object descriptions, they were challenged by environm…

cs.LG2024

DiffusionCounterfactuals: Inferring High-dimensional Counterfactuals with Guidance of Causal Representations

Jiageng Zhu, Hanchen Xie, Jiazhi Li +1

Accurate estimation of counterfactual outcomes in high-dimensional data is crucial for decision-making and understanding causal relationships and intervention outcomes in various d…

cs.LG2023

SABAF: Removing Strong Attribute Bias from Neural Networks with Adversarial Filtering

Jiazhi Li, Mahyar Khayatkhoei, Jiageng Zhu +3

Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for prediction is crucial in advancing fair and trustworthy AI. While several promising meth…

cs.LG20231 cited

Information-Theoretic Bounds on The Removal of Attribute-Specific Bias From Neural Networks

Jiazhi Li, Mahyar Khayatkhoei, Jiageng Zhu +3

Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for predictions is crucial in advancing fair and trustworthy AI. While several promising met…