1

Promoting Intersectional Fairness through Knowledge Distillation

Md Fahim Sikder, Resmi Ramachandranpillai, Daniel de Leng, Fredrik Heintz

Diff-Fair: Mitigating Intersectional Bias Through Diffusion-Driven Fair Representation

Md Fahim Sikder, Daniel de Leng, Fredrik Heintz

Fair4Free: Generating High-fidelity Fair Synthetic Samples using Data Free Distillation

Md Fahim Sikder, Daniel de Leng, Fredrik Heintz

FairX: A comprehensive benchmarking tool for model analysis using fairness, utility, and eXplainability

We present FairX, an open-source Python-based benchmarking tool designed for the comprehensive analysis of models under the umbrella of …

Md Fahim Sikder, Resmi Ramachandranpillai, Daniel de Leng, Fredrik Heintz

Generating Synthetic Fair Syntax-agnostic Data by Learning and Distilling Fair Representation

Md Fahim Sikder, Resmi Ramachandranpillai, Daniel de Leng, Fredrik Heintz

Generating Synthetic Fair Syntax-agnostic Data by Learning and Distilling Fair Representation

Generative Models for Time-Series and Fair Data Generation

Md Fahim Sikder, Resmi Ramachandranpillai, Daniel de Leng, Fredrik Heintz

Explainable Bengali Multiclass News Classification

The automatic classification of news articles is crucial in the era of information overflow as it assists readers in accessing relevant …

Md Fahim Sikder, Md Ferdous, Shraboni Afroz, Uzzal Podder, Kaniz Fatema, Mohammad Nahid Hossain, Md Tahmid Hasan, Mrinal Kanti Baowaly

Generating Private and Fair Long-Sequenced Longitudinal Healthcare Records

Generating long-sequenced longitudinal healthcare records is critical as it has numerous potential applications. Long-sequenced …

Md Fahim Sikder, Resmi Ramachandranpillai, Fredrik Heintz

Fair Latent Deep Generative Models (FLDGM) for Syntax-agnostic and Fair Synthetic Data Generation

Deep Generative Models (DGMs) for generating synthetic data with properties such as quality, diversity, fidelity, and privacy is an …

Resmi Ramachandranpillai, Md Fahim Sikder, Fredrik Heintz

Fair Latent Deep Generative Models (FLDGM) for Syntax-agnostic and Fair Synthetic Data Generation

Privacy-Preserving Synthetic Trajectory Data Generation

A major open research challenge is developing privacy-preserving machine learning methods that both achieve high performance and …

David Bergström, Md Fahim Sikder, Fredrik Heintz