Skip to content
View if-loops's full-sized avatar
26 followers · 20 following

Achievements

Achievement: Pull SharkAchievement: Starstruck

Achievements

Achievement: Pull SharkAchievement: Starstruck

Highlights

  • Pro

Block or report if-loops

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
if-loops/README.md

CV at a glance

Linkedin Google Scholar

Machine Unlearning

I work on making machine learning models forget undesired data without having to retrain the whole model ($$$). This can be privacy infringing, copyrighted, erroneous, poisoned, outdated or otherwise problematic data.

unlearning_explain (1)


Research

🪄:  Machine Unlearning Papers
Visual Title Authorship Venue
poison_wide Potion: Towards Poison Unlearning First Journal of Data-Centric Machine Learning Research (DMLR)
image Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening Equal Contrib. AAAI 2024
image Loss-Free Machine Unlearning Equal Contrib. ICLR 2024 Tiny Paper
image Parameter-Tuning-Free Data Entry Error Unlearning with Adaptive Selective Synaptic Dampening First Preprint
image Zero-Shot Machine Unlearning at Scale via Lipschitz Regularization 3rd Preprint
image Learning to Forget using Hypernetworks Co-supervised MPhil thesis NeurIPS 2024 Workshop
image CONDA: Fast Federated Unlearning with Contribution Dampening 4th Preprint
📖:  Other Research (Red Teaming, Agentic LLMs, and more)
Visual Title Authorship Venue
Screenshot 2024-08-16 at 14 56 29 Identifying contributors to manufacturing outcomes in a multi-echelon setting: a decentralised uncertainty quantification approach First IEEE Transactions on Industrial Informatics
packing Using Reinforcement Learning for the Three-Dimensional Loading Capacitated Vehicle Routing Problem First IJCAI 2023 Workshop
image Attack Atlas: A Practitioner’s Perspective on Challenges and Pitfalls in Red Teaming GenAI 2nd NeurIPS 2024 Workshop
image Agentic LLMs in the Supply Chain: Towards Autonomous Multi-Agent Consensus-Seeking Co-supervised MSc thesis Preprint

Off-topic

🖋️:  A tiny thing I made to make Google Scholar better

➡️ Author highlighter


scholar

Pinned Loading

  1. selective-synaptic-dampening selective-synaptic-dampening Public

    [AAAI, ICLR TP] Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening

    Python 41 8

  2. jwf40/Information-Theoretic-Unlearning jwf40/Information-Theoretic-Unlearning Public

    Code for the paper 'An Information Theoretic Approach to Machine Unlearning'

    Jupyter Notebook 21

  3. towards_poison_unlearning towards_poison_unlearning Public

    [DMLR] Potion: Towards Poison Unlearning

    Shell 1

  4. adaptive-selective-synaptic-dampening adaptive-selective-synaptic-dampening Public

    Jupyter Notebook 3

  5. 3L-CVRP 3L-CVRP Public

    IJCAI 2023 WOSEPCO: RL for the Three-Dimensional Loading Capacitated Vehicle Routing Problem

    Jupyter Notebook 4 3

  6. gpt-4o-system-prompt gpt-4o-system-prompt Public

    o1 and GPT-4o system prompts

    3 2