Implicit Bias

Implicit bias refers to unintended, often subtle, biases embedded within machine learning models, stemming from biases present in their training data. Current research focuses on detecting and mitigating these biases in various model architectures, particularly large language models (LLMs) and deep neural networks, using techniques like prompt engineering, fine-tuning, and Bayesian methods. Understanding and addressing implicit bias is crucial for ensuring fairness and equity in AI applications, impacting fields ranging from healthcare and criminal justice to education and hiring. The development of robust bias detection and mitigation strategies is a central goal of ongoing research.

Papers

November 30, 2023

Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
Kaifeng Lyu, Jikai Jin, Zhiyuan Li, Simon S. Du, Jason D. Lee, Wei Hu
Implicit Bias Regression Task Margin Classifier Grokking Phenomenon Homogeneous Neural Network

November 10, 2023

Minimum norm interpolation by perceptra: Explicit regularization and implicit bias
Jiyoung Park, Ian Pelakh, Stephan Wojtowytsch
Empirical Risk Minimization Implicit Bias Explicit Regularization Shallow ReLU Decay Regularization Minimum Norm

November 5, 2023

Hierarchical Simplicity Bias of Neural Networks
Zhehang Du
Neural Network Decision Tree Implicit Bias Simplicity Bias Predictive Power Label Relationship

November 1, 2023

Implicit biases in multitask and continual learning from a backward error analysis perspective
Benoit Dherin
Continual LEArning Stochastic Gradient Descent Multi Task Implicit Bias Implicit Regularization Task Gradient Flatness Aware

October 29, 2023

Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data
Yiwen Kou, Zixiang Chen, Quanquan Gu
Gradient Descent Gradient Flow Implicit Bias Two Layer ReLU Post Hoc Orthogonalization Leaky ReLU

October 26, 2023

September 27, 2023

Demographic Parity: Mitigating Biases in Real-World Data
Orestis Loukas, Ho-Ryun Chung
Synthetic Data Implicit Bias Real World Data Mitigating Bias Classification Application Demographic Parity

August 31, 2023

On the Implicit Bias of Adam
Matias D. Cattaneo, Jason M. Klusowski, Boris Shigida
Strong Generalization Implicit Bias Loss Gradient Gradient Descent Trajectory

August 24, 2023

Mind vs. Mouth: On Measuring Re-judge Inconsistency of Social Bias in Large Language Models
Yachao Zhao, Bo Wang, Dongming Zhao, Kun Huang, Yan Wang, Ruifang He, Yuexian Hou
Human Mind Social Bias Implicit Bias Inconsistency Measure

August 21, 2023

FairMonitor: A Four-Stage Automatic Framework for Detecting Stereotypes and Biases in Large Language Models
Yanhong Bai, Jiabao Zhao, Jinxin Shi, Tingjiang Wei, Xingjiao Wu, Liang He
Implicit Bias Stereotype Content Topic Bias Multi Dimensional Evaluation Stereotype Detection Multi Stage Framework

July 14, 2023

Othering and low status framing of immigrant cuisines in US restaurant reviews and large language models
Yiwei Luo, Kristina Gligorić, Dan Jurafsky
Large Language Model Implicit Bias Stereotype Content Low Priority Representational Harm Restaurant Review

July 7, 2023

Evaluating Biased Attitude Associations of Language Models in an Intersectional Context
Shiva Omrani Sabbaghi, Robert Wolfe, Aylin Caliskan
Language Model Implicit Bias Intersectional Bias Social Cognition Intersectional Social Attribute Intrinsic Evaluation Biased Association

June 30, 2023

The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks
Mor Shpigel Nacson, Rotem Mulayoff, Greg Ongie, Tomer Michaeli, Daniel Soudry
Implicit Bias ReLU Network Shallow Network Flat Minimum Shallow ReLU Layer ReLU Network

June 20, 2023

The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks
Yuan Cao, Difan Zou, Yuanzhi Li, Quanquan Gu
Stochastic Gradient Descent Batch Normalization Implicit Bias Deep Linear Linear Model Margin Classifier Linear Neural Network

June 14, 2023

Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
Nikhil Vyas, Depen Morwani, Rosie Zhao, Gal Kaplun, Sham Kakade, Boaz Barak
Deep Learning Stochastic Gradient Descent Online Learning Implicit Bias Offline Learning Gradient Step Rating Meaningfulness Multi Epoch Training

June 10, 2023

Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs
Dmitry Chistikov, Matthias Englert, Ranko Lazic
LeArning Abstract Gradient Flow Single Neuron Level Implicit Bias Teacher Network Shallow ReLU Single Neuron Layer ReLU Network Neural Interpolation

June 1, 2023

Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks
Dan Zhao
Deep Network Efficient Learning Implicit Bias Implicit Regularization Deep Linear Explicit Regularization Explicit Point Solo

May 25, 2023

Implicit bias of SGD in $L_{2}$-regularized linear DNNs: One-way jumps from high to low rank
Zihan Wang, Arthur Jacot
Stochastic Gradient Descent Low Rank Implicit Bias Matrix Completion Hidden Layer Deep Linear Linear Neural Network Local Minimum

May 24, 2023

Relating Implicit Bias and Adversarial Attacks through Intrinsic Dimension
Lorenzo Basile, Nikos Karantzas, Alberto D'Onofrio, Luca Bortolussi, Alex Rodriguez, Fabio Anselmi
Neural Network Adversarial Attack Implicit Bias Intrinsic Dimension Nonlinear Correlation

Implicit Bias

Papers

Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

Minimum norm interpolation by perceptra: Explicit regularization and implicit bias

Hierarchical Simplicity Bias of Neural Networks

Implicit biases in multitask and continual learning from a backward error analysis perspective

Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data

''Fifty Shades of Bias'': Normative Ratings of Gender Bias in GPT Generated English Text

Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult

Demographic Parity: Mitigating Biases in Real-World Data

On the Implicit Bias of Adam

Mind vs. Mouth: On Measuring Re-judge Inconsistency of Social Bias in Large Language Models

FairMonitor: A Four-Stage Automatic Framework for Detecting Stereotypes and Biases in Large Language Models

Othering and low status framing of immigrant cuisines in US restaurant reviews and large language models

Evaluating Biased Attitude Associations of Language Models in an Intersectional Context

The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks

The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks

Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning

Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs

Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks

Implicit bias of SGD in $L_{2}$-regularized linear DNNs: One-way jumps from high to low rank

Relating Implicit Bias and Adversarial Attacks through Intrinsic Dimension