Live briefing
Everything about Machine unlearning
Field of study in artificial intelligence
Machine unlearning is a branch of machine learning focused on removing specific undesired element, such as private data, wrong or manipulated training data, outdated information, copyrighted material, harmful content, dangerous abilities, or misinformation, without needing to rebuild models from the ground up. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: Machine unlearningA 5-minute orientation
- Skim a recent paper: Learn to Forget: Machine Unlearning via Neuron MaskingInfluential work since 2022
- Pick up a classic book: Understanding child abuse and neglectThe most-reprinted book on the subject
- Read the landmark paper: Fast Yet Effective Machine UnlearningCited 179 times
- Go sideways: Adversarial machine learningA closely related topic
- Go sideways: Hyperparameter optimizationA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
Fast Yet Effective Machine Unlearning
Zero-Shot Machine Unlearning
Machine Unlearning: A Survey
A Survey of Machine Unlearning
Rethinking machine unlearning for large language models
Machine Unlearning: Solutions and Challenges
Machine unlearning: linear filtration for logit-based classifiers
A Review on Machine Unlearning
🆕 Influential since 2022
Learn to Forget: Machine Unlearning via Neuron Masking
Athena: Probabilistic Verification of Machine Unlearning
Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects
Threats, Attacks, and Defenses in Machine Unlearning: A Survey
Learn to Unlearn: Insights Into Machine Unlearning
📚 Books worth reading
- 📕Understanding child abuse and neglectCynthia Crosson-Tower · 2010
- 📕The motion of fluids, natural and artificial...Martin Clare · 1735
Envisioning the pastSam Smiles, Stephanie Moser · 2005
Outcast EuropeSharif Gemie · 2011- 📕The motion of fluids, natural and artificialM. Clare · 1735
- 📕Postcolonial literatures and DeleuzeLorna Burns, Birgit Mara Kaiser · 2012
Machine, UnlearningLi Zilles · 2018- 📕Unlearning the citySwati Chattopadhyay · 2012
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Adversarial machine learning Adversarial machine learning is the study of the attacks on machine learning algorithms, and of the defenses against such attacks. Machine learning techniques…
- Hyperparameter optimization In machine learning, hyperparameter optimization or tuning is the problem of choosing a set of optimal hyperparameters for a learning algorithm. A hyperparamete…
- Model inversion attack Model inversion attack is a type of adversarial machine learning attack where an attacker tries to reconstruct or infer sensitive information about a model's…
- Training, validation, and test data sets In machine learning, a common task is the study and construction of algorithms that can learn from and make predictions on data. Such algorithms function…
- Meta-learning (computer science) Meta-learning is a subfield of machine learning where automatic learning algorithms are applied to metadata about machine learning experiments. As of 2017…
- Online machine learning In computer science, online machine learning is a method of machine learning in which data becomes available in a sequential order and is used to update…
- Differentially private stochastic gradient descent Differentially private stochastic gradient descent (DP-SGD) is an algorithmic technique for learning and a refined analysis of privacy costs within the…
- Federated learning Federated learning (also known as collaborative learning) is a machine learning technique in a setting where multiple entities (often called clients) collaborat…