Md Fahim Sikder

Ph.D. Student

Linköping University

Biography

Md Fahim Sikder is currently pursuing his Ph.D. under the guidance of Professor Fredrik Heintz and Assistant Professor Daniel de Leng at the Reasoning and Learning (ReaL) Lab, IDA, Linköping University, Sweden. His research focuses on creating Generative Models for Time-Series and Fair Data Generation. Before this, Fahim served as a Lecturer in the Computer Science and Engineering department at the Institute of Science, Trade, and Technology (ISTT). He also took on the roles of Coordinator of the HEAP Programming Club and Coach of the ACM ICPC team at ISTT.

Fahim’s research interests include Artificial Intelligence, Generative Models, Trustworthy AI.

Md Fahim Sikder conducted several workshops and seminars, including a Workshop on Latex and a Week-long training course on Python (Beginning to Advance including Machine Learning). He participated in several National and International Contests. He achieved many titles, including “Champion at International Contest on Programming and System Development (ICPSD), 2014”, and “Champion at NASA SPACE APPS CHALLENGE 2016” in Rajshahi Region, Bangladesh.

Interests

Artificial Intelligence
Deep Learning
Generative Models
Time-Series Generation
Trustworthy AI
Data Fairness
Explainable AI (XAI)
Robotics

Education

Ph.D. in Computer Science, Ongoing

Linköping University, Sweden
Master of Science in Computer Science, 2018

Jahangirnagar University, Bangladesh
Bachelor of Science (Engineering) in Computer Science & Engineering, 2016

Gopalganj Science and Technology University, Bangladesh (Formerly- Bangabandhu Sheikh Mujibur Rahman Science and Technology University)
Higher Secondary Certificate Examination, 2012

Khilgaon Government High School, Bangladesh
Secondary School Certificate Examination, 2010

Khilgaon Government High School, Bangladesh

Experience

Ph.D. Student

Linköping University

April 2020 – Present Linköping, Sweden

Department of Computer and Information Science (IDA)

Responsibilities include:

Research
Supervising Master’s Thesis
Conducting Labs
Chair, IDA PhD Council (Board: 2024)
Presidium Member, Linköping University PhD Student Network (LiU PhD) (Board: 2024/25)
Department Representative (IDA), Linköping University PhD Student Network (LiU PhD) (Board: 2023/24)

Lecturer

Institute of Science Trade & Technology (ISTT)

July 2017 – February 2020 Dhaka, Bangladesh

Department of Computer Science & Engineering (CSE)

Responsibilities include:

Conducting Class & Labs
Research
Supervising Research Students

Featured Publications

Md Fahim Sikder, Resmi Ramachandranpillai, Fredrik Heintz

April, 2025 Accepted at Machine Learning with Application publication

TransFusion: Generating Long, High-Fidelity Time Series using Diffusion Models with Transformers

The generation of high-quality, long-sequenced time-series data is essential due to its wide range of applications. In the past, standalone Recurrent and Convolutional Neural Network-based Generative Adversarial Networks (GAN) were used to synthesize time-series data. However, they are inadequate for generating long sequences of time-series data due to limitations in the architecture. Furthermore, GANs are well known for their training instability and mode collapse problem. To address this, we propose TransFusion, a diffusion, and transformers-based generative model to generate high-quality long-sequence time-series data. We have stretched the sequence length to 384, and generated high-quality synthetic data. Also, we introduce two evaluation metrics to evaluate the quality of the synthetic data as well as its predictive characteristics. We evaluate TransFusion with a wide variety of visual and empirical metrics, and TransFusion outperforms the previous state-of-the-art by a significant margin.

Recent Publications

Md Fahim Sikder, Daniel de Leng, Fredrik Heintz (2025). Mitigating Intersectional Bias Through Diffusion-Driven Fair Representation. Work in Progress.

Md Fahim Sikder, Daniel de Leng, Fredrik Heintz (2024). Fair4Free: Generating High-fidelity Fair Synthetic Samples using Data Free Distillation. Work in Progress.

PDF Cite

Md Fahim Sikder, Resmi Ramachandranpillai, Daniel de Leng, Fredrik Heintz (2024). FairX: A comprehensive benchmarking tool for model analysis using fairness, utility, and eXplainability. AEQUITAS, co-located with ECAI 2024.

PDF Cite Code Slides

Md Fahim Sikder, Resmi Ramachandranpillai, Daniel de Leng, Fredrik Heintz (2024). Generating Synthetic Fair Syntax-agnostic Data by Learning and Distilling Fair Representation. Work in Progress.

PDF Cite

Resmi Ramachandranpillai, Md Fahim Sikder, David Bergström, Fredrik Heintz (2024). Bt-GAN: Generating Fair Synthetic Healthdata via Bias-transforming Generative Adversarial Networks. JAIR.

PDF Cite Dataset DOI

See all publications

Accomplishments

Call to Arms Award (Reviewer), 26th European Conference on Artificial Intelligence (ECAI 2023), 2023
Program Committee Member, 26th European Conference on Artificial Intelligence (ECAI 2023), 2023
Program Committee Member, 18th Swedish National Computer Networking and Cloud Computing Workshop (SNCNW 2023), 2023
Finalist, Student Project Competition, Linköping Hockey Analytics Conference (LINHAC) 2022, 2022
NVIDIA GPU Grant, NVIDIA, 2018
Champion, NASA Space Apps Challenge 2016, Rajshahi Region, Bangladesh, 2016
Best Young Inventor, Digital Innovation Fair 2016, 2016
Champion, Project Showcasing(Mobile Apps), CSE IT Carnival 2015, BSMRSTU, 2015
Champion, International Contest on Programming & System Development (ICPSD) 2014, System Development Section, 2014