SAFE: Machine Unlearning With Shard Graphs
- URL: http://arxiv.org/abs/2304.13169v2
- Date: Tue, 22 Aug 2023 16:42:25 GMT
- Title: SAFE: Machine Unlearning With Shard Graphs
- Authors: Yonatan Dukler, Benjamin Bowman, Alessandro Achille, Aditya Golatkar,
Ashwin Swaminathan, Stefano Soatto
- Abstract summary: We present Synergy Aware Forgetting Ensemble (SAFE), a method to adapt large models on a diverse collection of data.
SAFE uses a lightweight system of adapters which can be trained while reusing most of the computations.
This allows SAFE to be trained on shards an order-of-magnitude smaller than current state-of-the-art methods.
- Score: 100.12621304361288
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We present Synergy Aware Forgetting Ensemble (SAFE), a method to adapt large
models on a diverse collection of data while minimizing the expected cost to
remove the influence of training samples from the trained model. This process,
also known as selective forgetting or unlearning, is often conducted by
partitioning a dataset into shards, training fully independent models on each,
then ensembling the resulting models. Increasing the number of shards reduces
the expected cost to forget but at the same time it increases inference cost
and reduces the final accuracy of the model since synergistic information
between samples is lost during the independent model training. Rather than
treating each shard as independent, SAFE introduces the notion of a shard
graph, which allows incorporating limited information from other shards during
training, trading off a modest increase in expected forgetting cost with a
significant increase in accuracy, all while still attaining complete removal of
residual influence after forgetting. SAFE uses a lightweight system of adapters
which can be trained while reusing most of the computations. This allows SAFE
to be trained on shards an order-of-magnitude smaller than current
state-of-the-art methods (thus reducing the forgetting costs) while also
maintaining high accuracy, as we demonstrate empirically on fine-grained
computer vision datasets.
Related papers
- Semi-Supervised Reward Modeling via Iterative Self-Training [52.48668920483908]
We propose Semi-Supervised Reward Modeling (SSRM), an approach that enhances RM training using unlabeled data.
We demonstrate that SSRM significantly improves reward models without incurring additional labeling costs.
Overall, SSRM substantially reduces the dependency on large volumes of human-annotated data, thereby decreasing the overall cost and time involved in training effective reward models.
arXiv Detail & Related papers (2024-09-10T22:57:58Z) - Learning Augmentation Policies from A Model Zoo for Time Series Forecasting [58.66211334969299]
We introduce AutoTSAug, a learnable data augmentation method based on reinforcement learning.
By augmenting the marginal samples with a learnable policy, AutoTSAug substantially improves forecasting performance.
arXiv Detail & Related papers (2024-09-10T07:34:19Z) - VIRL: Volume-Informed Representation Learning towards Few-shot Manufacturability Estimation [0.0]
This work introduces VIRL, a Volume-Informed Representation Learning approach to pre-train a 3D geometric encoder.
The model pre-trained by VIRL shows substantial enhancements on demonstrating improved generalizability with limited data.
arXiv Detail & Related papers (2024-06-18T05:30:26Z) - $\nabla τ$: Gradient-based and Task-Agnostic machine Unlearning [7.04736023670375]
We introduce Gradient-based and Task-Agnostic machine Unlearning ($nabla tau$)
$nabla tau$ applies adaptive gradient ascent to the data to be forgotten while using standard gradient descent for the remaining data.
We evaluate our framework's effectiveness using a set of well-established Membership Inference Attack metrics.
arXiv Detail & Related papers (2024-03-21T12:11:26Z) - Fast Machine Unlearning Without Retraining Through Selective Synaptic
Dampening [51.34904967046097]
Selective Synaptic Dampening (SSD) is a fast, performant, and does not require long-term storage of the training data.
We present a novel two-step, post hoc, retrain-free approach to machine unlearning which is fast, performant, and does not require long-term storage of the training data.
arXiv Detail & Related papers (2023-08-15T11:30:45Z) - Self-Damaging Contrastive Learning [92.34124578823977]
Unlabeled data in reality is commonly imbalanced and shows a long-tail distribution.
This paper proposes a principled framework called Self-Damaging Contrastive Learning to automatically balance the representation learning without knowing the classes.
Our experiments show that SDCLR significantly improves not only overall accuracies but also balancedness.
arXiv Detail & Related papers (2021-06-06T00:04:49Z) - Self-Supervised Pretraining Improves Self-Supervised Pretraining [83.1423204498361]
Self-supervised pretraining requires expensive and lengthy computation, large amounts of data, and is sensitive to data augmentation.
This paper explores Hierarchical PreTraining (HPT), which decreases convergence time and improves accuracy by initializing the pretraining process with an existing pretrained model.
We show HPT converges up to 80x faster, improves accuracy across tasks, and improves the robustness of the self-supervised pretraining process to changes in the image augmentation policy or amount of pretraining data.
arXiv Detail & Related papers (2021-03-23T17:37:51Z) - Balanced Softmax Cross-Entropy for Incremental Learning [6.5423218639215275]
Deep neural networks are prone to catastrophic forgetting when incrementally trained on new classes or new tasks.
Recent methods has proven to be effective to mitigate catastrophic forgetting.
We propose the use of the Balanced Softmax Cross-Entropy loss and show that it can be combined with exiting methods for incremental learning to improve their performances.
arXiv Detail & Related papers (2021-03-23T13:30:26Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.