Frederik Träuble

Ashish Malik

Hugo Larochelle

Michael Curtis Mozer

Sanjeev Arora

Machine unlearning, which involves erasing knowledge about a \emph{forget set} from a trained model, can prove to be costly and infeasible … (see more)using existing techniques. We propose a low-compute unlearning technique based on a discrete representational bottleneck. We show that the proposed technique efficiently unlearns the forget set and incurs negligible damage to the model's performance on the rest of the dataset. We evaluate the proposed technique on the problem of class unlearning using four datasets: CIFAR-10, CIFAR-100, LACUNA-100 and ImageNet-1k. We compare the proposed technique to SCRUB, a state-of-the-art approach which uses knowledge distillation for unlearning. Across all four datasets, the proposed technique performs as well as, if not better than SCRUB while incurring almost no computational cost.

2025-09-15

TMLR (accepted)

Unlearning via Sparse Representations

Vedant Shah

Ashish Malik

Hugo Larochelle

Michael Curtis Mozer

Sanjeev Arora

2023-11-26

ArXiv (preprint)

Unlearning via Sparse Representations

Vedant Shah

Ashish Malik

Hugo Larochelle

Michael Curtis Mozer

Sanjeev Arora

Machine \emph{unlearning}, which involves erasing knowledge about a \emph{forget set} from a trained model, can prove to be costly and infea… (see more)sible by existing techniques. We propose a nearly compute-free zero-shot unlearning technique based on a discrete representational bottleneck. We show that the proposed technique efficiently unlearns the forget set and incurs negligible damage to the model's performance on the rest of the data set. We evaluate the proposed technique on the problem of \textit{class unlearning} using three datasets: CIFAR-10, CIFAR-100, and LACUNA-100. We compare the proposed technique to SCRUB, a state-of-the-art approach which uses knowledge distillation for unlearning. Across all three datasets, the proposed technique performs as well as, if not better than SCRUB while incurring almost no computational cost.

2023-11-26

ArXiv (preprint)

arxiv.org

Discrete Key-Value Bottleneck

Nasim Rahaman

Michael Curtis Mozer

Kenji Kawaguchi

Bernhard Schölkopf

2023-07-03

Proceedings of the 40th International Conference on Machine Learning (published)

A General-Purpose Neural Architecture for Geospatial Systems

Nasim Rahaman

Martin Weiss

Francesco Locatello

Alexandre Lacoste

Chris Pal

Li Erran Li

Bernhard Schölkopf

2022-11-02

OpenReview.net/Anonymous_Preprint (unknown)

CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning

Manuel Wüthrich

Bernhard Schölkopf

Despite recent successes of reinforcement learning (RL), it remains a challenge for agents to transfer learned skills to related environment… (see more)s. To facilitate research addressing this problem, we proposeCausalWorld, a benchmark for causal structure and transfer learning in a robotic manipulation environment. The environment is a simulation of an open-source robotic platform, hence offering the possibility of sim-to-real transfer. Tasks consist of constructing 3D shapes from a set of blocks - inspired by how children learn to build complex structures. The key strength of CausalWorld is that it provides a combinatorial family of such tasks with common causal structure and underlying factors (including, e.g., robot and object masses, colors, sizes). The user (or the agent) may intervene on all causal variables, which allows for fine-grained control over how similar different tasks (or task distributions) are. One can thus easily define training and evaluation distributions of a desired difficulty level, targeting a specific form of generalization (e.g., only changes in appearance or object mass). Further, this common parametrization facilitates defining curricula by interpolating between an initial and a target task. While users may define their own task distributions, we present eight meaningful distributions as concrete benchmarks, ranging from simple to very challenging, all of which require long-horizon planning as well as precise low-level motor control. Finally, we provide baseline results for a subset of these tasks on distinct training curricula and corresponding evaluation protocols, verifying the feasibility of the tasks in this benchmark.

2021-01-12

ICLR.cc/2021/Conference (poster)