New framework for auditing machine unlearning
Algorithms & Theory
More from the blog
Paving the way for greener ammonia production
New MIT research could lead to better materials for a fossil-fuel-free process for making the chemical that's essential to fertilizer and other products.
When AI art has no author: Study finds generated images often can’t be traced to training data
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
Putting sign language AI into users’ hands
Introducing sign-language-to-text (SL2T), our breakthrough model powering new sign language features for Deaf and hard of hearing users.
Alexander Rakhlin named director of the MIT Statistics and Data Science Center
An expert in machine learning, statistics, and computation, Rakhlin succeeds Professor Ankur Moitra.
Related papers
Stability-aware multi-objective federated learning via deep reinforcement learning: Client selection and resource optimization in dynamic edge networks
Anomaly detection method for satellite networks based on adaptive federated learning driven by deep reinforcement learning
Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket
This work introduces a pioneering exploration of Self-Supervised Learning (SSL) within the SNN, and proposes a novel Spiking Self-Attention (SSA) and Spiking Transformer (Spikformer) that achieves 80+% accuracy on ImageNet.
EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction
EquiPocket is proposed, an E(3)-equivariant Graph Neural Network for binding site prediction, which comprises three modules: the first one to extract local geometric information for each surface atom, the second one to model both the chemical and spatial structure of protein and the last one to capture the geometry of the surface via equivariant message passing over the surface atoms.