Milad Khademi Nori
Milad Khademi Nori

Milad Khademi Nori, PhD

Postdoctoral Fellow

Department of Computer Science, Toronto Metropolitan University, Toronto

mkn [at] torontomu [dot] ca  |  miladkhademinori [at] gmail [dot] com

I build the mathematics of continual learning: task-confusion bounds that explain when forgetting must occur, the geometry of pre-trained representations that explains when it need not, and memory policies for continually learning agents.

About

About me

I am a Postdoctoral Fellow in the Department of Computer Science at Toronto Metropolitan University, working with Prof. Guanghui (Richard) Wang on continual and federated learning with pre-trained models. I earned my PhD in Electrical and Computer Engineering from Queen's University in 2024, supervised by Prof. Il-Min Kim, with a thesis on federated and incremental learning, completed within the Huawei-funded doctoral research program.

My research gives continual learning a mathematical foundation. The starting point is a simple observation: models that keep learning after deployment forget, and the field lacked a theory of when forgetting is unavoidable. My task-confusion framework proved that discriminative learners trained in stages are infeasible in general; the margin and gauge results that followed show what property of a pre-trained representation lifts that infeasibility, and by how much, in closed form; and my current work turns the same quantities into provable memory policies for agents that must decide what to keep, what to consolidate into weights, and what to forget.

Every result in this line was produced on a single workstation GPU: the program is deliberately reproducible by any group, without cluster access.

At a glance

  • PublicationsNeurIPS, ICLR and ICML first-author papers within two years of the PhD, plus IEEE journal papers
  • DoctorateQueen's University, 2024, in four years and four months while publishing
  • ReviewingSix years for ICML, NeurIPS, ICLR, CVPR and AAAI, and three IEEE Transactions
  • TeachingFour years of instruction and laboratories at Queen's, about 110 students per week at peak
  • Class rankingsRanked first in both the M.Sc. and B.Sc. graduating classes

Research

Research interests

Theory of continual learning

Task-confusion bounds, infeasibility theorems, and exponential-decay margins: when forgetting must happen, when it need not, and the quantities that decide.

Geometry of pre-trained models

Why frozen and lightly adapted backbones evade the classical limits: margins, head gauge, and certificates computable before training.

Federated learning

Learning across clients without shared data: communication trade-offs, non-IID heterogeneity, and federated incremental learning.

Memory for continual agents

What an agent should write to memory, when to consolidate into weights, and what to forget: rent-or-buy ledgers and policies with guarantees.

News

Recent news

2025

Paper accepted at ICML 2025 (Vancouver): autoencoder-based hybrid replay for class-incremental learning; presented in person.

2025

Travel award from the Faculty of Science, Toronto Metropolitan University, to present at ICML 2025.

2025

Paper accepted at ICLR 2025 (Singapore): federated class-incremental learning with latent exemplars and data-free techniques; presented in person.

2024

Paper accepted at NeurIPS 2024 (Vancouver): the task-confusion framework for class-incremental learning; presented in person.

2024

Completed the PhD at Queen's University (January 2024) and joined Toronto Metropolitan University as a Postdoctoral Fellow (March 2024).

Publications

Selected publications

2025

Autoencoder-based hybrid replay for class-incremental learning

Milad Khademi Nori, Il-Min Kim, Guanghui Wang

ICML 2025 arXiv
BibTeX
@inproceedings{nori2025autoencoder,
  author    = {Khademi Nori, Milad and Kim, Il-Min and Wang, Guanghui},
  title     = {Autoencoder-based hybrid replay for class-incremental learning},
  booktitle = {International Conference on Machine Learning (ICML)},
  year      = {2025}
}

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 arXiv
BibTeX
@inproceedings{nori2025federated,
  author    = {Khademi Nori, Milad and Kim, Il-Min and Wang, Guanghui},
  title     = {Federated class-incremental learning: a hybrid approach using latent exemplars and data-free techniques to address local and global forgetting},
  booktitle = {International Conference on Learning Representations (ICLR)},
  pages     = {84398--84411},
  year      = {2025}
}
2024

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 arXiv
BibTeX
@inproceedings{nori2024task,
  author    = {Khademi Nori, Milad and Kim, Il-Min},
  title     = {Task confusion and catastrophic forgetting in class-incremental learning: a mathematical framework for discriminative and generative modelings},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  volume    = {37},
  pages     = {47678--47707},
  year      = {2024}
}
2023 and earlier

On the effectiveness of activation noise in both training and inference for generative classifiers

Milad Khademi Nori, Yiqun Ge, Il-Min Kim

IEEE Access vol. 11, pp. 131623-131638

Fast federated learning by balancing communication trade-offs

Milad Khademi Nori, Sangseok Yun, Il-Min Kim

IEEE Transactions on Communications vol. 69, no. 8, pp. 5168-5182 IEEEarXiv

EDMARA2: a hierarchical routing protocol for EH-WSNs

Milad Khademi Nori, Saeed Sharifian

Wireless Networks vol. 26, no. 6, pp. 4303-4317 Springer

A QGSA cluster head selection approach for hierarchical routing protocol in the EH-WSNs

Milad Khademi Nori, Saeed Sharifian

ICSPIS 2018 IEEE
In addition, six first-author manuscripts are under review at NeurIPS 2026 and AAAI 2027, spanning a margin bound on task confusion, a gauge-anchoring fix for regularized cross-entropy heads, closed-form replay theory, long-tailed incremental learning, a neural-collapse diagnostic, and damped fine-tuning.

Education

Education

2019 - 2024

PhD, Electrical and Computer Engineering

Queen's University, Kingston, Canada

Thesis: Federated Learning and Incremental Learning: Private Non-IID Learning. Supervisor: Prof. Il-Min Kim. Completed as part of the Huawei-funded doctoral research program, with semi-annual reviews at Huawei Canada, Ottawa.

2016 - 2019

M.Sc., Electrical Engineering, ranked first in the class

Amirkabir University of Technology, Tehran

Thesis: an energy-efficient routing protocol for energy-harvesting wireless sensor networks in the IoT. Supervisor: Prof. Saeed Sharifian.

2012 - 2016

B.Sc., Electrical Engineering, ranked first in the class

Semnan University, Semnan, Iran

Digital electronic systems. Supervisor: Prof. Naser Eskandarian. Capstone: a Bluetooth-controlled quadcopter.

Experience

Experience

Mar 2024 - present

Postdoctoral Fellow

Department of Computer Science, Toronto Metropolitan University

Continual and federated learning with pre-trained models, with Prof. Guanghui (Richard) Wang. All published results of the appointment were produced on a single workstation GPU.

Jan 2023 - Apr 2024

Research Assistant

Queen's University, Innovation Park

Exploratory analysis of prostate-cancer datasets with Prof. Sidney Givigi: CT volumes, mass spectrometry, cleaning and preprocessing, volumetric data, landmark registration, four technical reports.

Aug 2019 - Nov 2023

Doctoral Researcher, Huawei-funded program

Queen's University with Huawei Technologies Canada, Ottawa

Non-IID deep learning: federated learning under communication burden and heterogeneity; continual learning, forgetting and task confusion. Semi-annual in-person research presentations.

2019 - 2023

Instructor, Lab Instructor, Teaching Assistant

Department of Electrical and Computer Engineering, Queen's University

MATLAB programming and mathematics (about 110 students per week) and Python for discrete-time signal processing (about 90 students); laboratories and mentoring.

2019 - 2023

Vice-President, speaker, public-relations chair

Ingenuity Lab, Queen's University

Public talks on the impacts of artificial intelligence; undergraduate mentoring.

Jan 2017 - Apr 2019

Network Specialist

Huawei Technologies, Tehran

Network equipment; taught internal networking classes; Huawei Certified Network Associate.

Awards

Awards and honors

Teaching

Teaching

Courses, Queen's ECE

  • MATLAB programming and mathematics: instructor and lab instructor, about 110 students per week
  • Python for discrete-time signal processing: instructor and lab instructor, about 90 students
  • Teaching assistant across four academic years, including mentoring and marking

Talks

  • ICML 2025, Vancouver: autoencoder-based hybrid replay
  • ICLR 2025, Singapore: federated class-incremental learning
  • NeurIPS 2024, Vancouver: task confusion and catastrophic forgetting
  • ICSPIS 2018, and semi-annual research presentations at Huawei Canada, 2019 to 2023
  • Public talks on artificial intelligence with the Ingenuity Lab, Queen's

Service

Reviewing and service

Conferences

  • Reviewer since 2021 for ICML, NeurIPS, ICLR, CVPR and AAAI
  • Serving as a reviewer for NeurIPS 2026 and AAAI 2027 in the current cycle

Journals

  • IEEE Transactions on Communications
  • IEEE/ACM Transactions on Networking
  • IEEE Transactions on Pattern Analysis and Machine Intelligence

Contact

Contact

Department of Computer Science, Toronto Metropolitan University, Toronto, Ontario, Canada.
Email: mkn [at] torontomu [dot] ca  |  miladkhademinori [at] gmail [dot] com