publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2025

  1. SD^2: Self-Distilled Sparse Drafters
    Mike Lasby, Nish Sinnadurai, Valavan Manohararajah, Sean Lie, Yani Ioannou, and Vithursan Thangarasa
    In ES-FoMo III: 3rd Workshop on Efficient Systems for Foundation Models, ICML Workshops, Jul 2025
  2. Backdooring VLMs via Concept-Driven Triggers
    Yufan Feng, Weimin Lyu, Yuxin Wang, Benjamin Tan, and Yani Ioannou
    In Data in Generative Models - The Bad, the Ugly, and the Greats (DIG-BUGS), ICML Workshops, Jul 2025
  3. Exploring Functional Similarities of Backdoored Models
    Yufan Feng, Benjamin Tan, and Yani Ioannou
    In ICML Workshop on Technical AI Governance (TAIG), Jul 2025
  4. Understanding Normalization Layers for Sparse Training
    Mohammed Adnan, Ekansh Sharma, Rahul Krishnan, and Yani Ioannou
    In 3rd Workshop on High-dimensional Learning Dynamics (HiLD), ICML Workshops, Jul 2025
  5. Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
    Mohammed AdnanRohan Jain, Ekansh Sharma, Rahul Krishnan, and Yani Ioannou
    In Forty-second International Conference on Machine Learning (ICML), Jul 2025
  6. SD^2: Self-Distilled Sparse Drafters
    Mike Lasby, Nish Sinnadurai, Valavan Manohararajah, Sean Lie, Yani Ioannou, and Vithursan Thangarasa
    Apr 2025
  7. What is Left After Distillation? How Knowledge Transfer Impacts Fairness and Bias
    Aida Mohammadshahi, and Yani Ioannou
    Transactions on Machine Learning Research (TMLR), Mar 2025
  8. Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry
    Mohammed AdnanRohan Jain, Ekansh Sharma, Rahul Krishnan, and Yani Ioannou
    In Conference on Parsimony and Learning (Recent Spotlight Track), Mar 2025

2024

  1. Long-Tail Learning with Language Model Guided Curricula
    Mohammed Adnan, Rahul Krishnan, and Yani Ioannou
    In Muslims in ML (MusIML) Workshop, NeurIPS 2024 Workshops, Dec 2024
  2. A Closer Look at Sparse Training in Deep Reinforcement Learning
    Muhammad Athar Ganaie, Vincent Michalski, Samira Ebrahimi Kahou, and Yani Ioannou
    In Muslims in ML (MusIML) Workshop, NeurIPS 2024 Workshops, Dec 2024
  3. Navigating Extremes: Dynamic Sparsity in Large Output Spaces
    Nasib Ullah, Erik Schultheis, Mike LasbyYani Ioannou, and Rohit Babbar
    In 38th Annual Conference Neural Information Processing Systems (NeurIPS), Dec 2024
  4. Winning Tickets from Random Initialization: Aligning Masks for Sparse Training
    Rohan JainMohammed Adnan, Ekansh Sharma, and Yani Ioannou
    In 2nd Workshop on Unifying Representations in Neural Models (UniReps), NeurIPS 2024 Workshops, Dec 2024
  5. What’s Left After Distillation? How Knowledge Transfer Impacts Fairness and Bias
    Aida Mohammadshahi, and Yani Ioannou
    In 19th Workshop for Women in Machine Learning (WiML), NeurIPS 2024 Workshops, Dec 2024
  6. Learning to Reweight Examples in Backdoor Defense
    Yufan Feng, Benjamin Tan, and Yani Ioannou
    In 19th Workshop for Women in Machine Learning (WiML), NeurIPS 2024 Workshops, Dec 2024
  7. Learning Parameter Sharing with Tensor Decompositions and Sparsity
    Cem ÜyükMike Lasby, Mohamed Yassin, Utku Evci, and Yani Ioannou
    arXiv preprint arXiv:2411.09816, Nov 2024
  8. SelfXit: An Unsupervised Early Exit Mechanism for Deep Neural Networks
    Hossein KhademSohi, Mohammadamin Abedi, Yani Ioannou, STEVE DREW, Pooyan Jamshidi, and Hadi Hemmati
    Transactions on Machine Learning Research (TMLR), Oct 2024
  9. Trustworthy and Responsible AI for Human-Centric Autonomous Decision-Making Systems
    Farzaneh Dehghani, Mahsa Dibaji, Fahim Anzum, Lily Dey, Alican Basdemir, Sayeh Bayat, Jean-Christophe Boucher, Steve Drew, Sarah Elaine Eaton, Richard Frayne, and 16 more authors
    arXiv preprint arXiv:2410.08407, Aug 2024
  10. Dynamic Sparse Training with Structured Sparsity
    Mike Lasby, Anna Golubeva, Utku Evci, Mihai Nica, and Yani Ioannou
    In International Conference on Learning Representations (ICLR), May 2024
  11. Dynamic Sparse Training with Structured Sparsity
    Mike Lasby, Anna Golubeva, Utku Evci, Mihai Nica, and Yani Ioannou
    In Conference on Parsimony and Learning (CPAL) Recent Spotlight Track, Jan 2024
  12. Classification Bias on a Data Diet
    Tejas PoteMohammed Adnan, Yigit Yargic, and Yani Ioannou
    In Conference on Parsimony and Learning (CPAL) Recent Spotlight Track, Jan 2024

2023

  1. Meta-GCN: A Dynamically Weighted Loss Minimization Method for Dealing with the Data Imbalance in Graph Neural Networks
    Mahdi Mohammadizadeh, Arash Mozhdehi, Yani Ioannou, and Xin Wang
    In 36th Canadian Conference on Artificial Intelligence, Canadian AI, CANAI 2023, Montreal, Canada, June 5-9, 2023, Proceedings, Jan 2023
  2. Bounding generalization error with input compression: An empirical study with infinite-width networks
    Angus Galloway, Anna Golubeva, Mahmoud Salem, Mihai Nica, Yani A. Ioannou, and Graham W. Taylor
    Transactions on Machine Learning Research (TMLR), Jan 2023

2022

  1. Monitoring Shortcut Learning using Mutual Information
    Mohammed AdnanYani Ioannou, Chuan-Yung Tsai, Angus Galloway, H. R. Tizhoosh, and Graham W. Taylor
    In ICML 2022 Workshop on Spurious Correlations, Invariance, and Stability, Jul 2022
  2. Condensing Sparse Layers
    Anna Golubeva, Mike LasbyYani Ioannou, and Mihai Nica
    In 2nd Workshop on Sparsity in Neural Networks, Jul 2022
  3. Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win
    Utku Evci, Yani A. Ioannou, Cem Keskin, and Yann Dauphin
    In Proceedings of the 36th AAAI Conference on Artificial Intelligence, Feb 2022

2021

  1. Domain-Agnostic Clustering with Self-Distillation
    Mohammed AdnanYani Ioannou, Chuan-Yung Tsai, and Graham Taylor
    In 2nd NeurIPS Workshop on Self-Supervised Learning: Theory and Practice, Nov 2021