Milad Khademi Nori

Postdoc, ECE, Toronto Metropolitan University

Joined

May 2022

Names

Milad Khademi Nori (Preferred)

Emails

****@queensu.ca (Confirmed)

,

****@torontomu.ca (Confirmed)

Personal Links

Career & Education History

Postdoc

ECE, Toronto Metropolitan University (torontomu.ca)

2024 – 2026

PhD student

ECE, Queen's University (queensu.ca)

2019 – 2024

Advisors, Relations & Conflicts

Postdoc Advisor

2024 – 2025

PhD Advisor

2019 – 2024

Expertise

Federated Learning

2019 – 2024

Incremental Learning

2019 – 2024

Artificial neural networks

2019 – 2024

Publications

ReMoBA: Representative Replay and Mixture of BatchNoise Autoencoders for Pre-Trained Model-Based Federated Domain-Incremental Learning
Milad Khademi Nori, Il-Min Kim, Guanghui Wang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Autoencoder-Based Hybrid Replay for Class-Incremental Learning
Milad Khademi Nori, IL MIN KIM, Guanghui Wang
- ICML 2025 poster
- Readers: Everyone
Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting
Milad Khademi Nori, IL MIN KIM, Guanghui Wang
- ICLR 2025 Poster
- Readers: Everyone
Autoencoder-Based Hybrid Replay for Class-Incremental Learning
Milad Khademi Nori, IL MIN KIM, Guanghui Wang
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings
Milad Khademi Nori, IL MIN KIM
- NeurIPS 2024 poster
- Readers: Everyone
On the Effectiveness of Activation Noise in Both Training and Inference for Generative Classifiers
Milad Khademi Nori, Yiqun Ge, Il-Min Kim
- IEEE Access 2023
- Readers: Everyone
ON INJECTING NOISE DURING INFERENCE
Milad Khademi Nori, Yiqun GE, IL MIN KIM
- Published: 01 Feb 2023, Last Modified: 13 Feb 2023
- Submitted to ICLR 2023
- Readers: Everyone
Fast Federated Learning by Balancing Communication Trade-Offs
Milad Khademi Nori, Sangseok Yun, Il-Min Kim
- CoRR 2021
- Readers: Everyone

Co-Authors