Forgetting Outside the Box: Scrubbing Deep Networks of Information
Accessible from Input-Output Observations
- URL: http://arxiv.org/abs/2003.02960v3
- Date: Thu, 29 Oct 2020 02:23:28 GMT
- Title: Forgetting Outside the Box: Scrubbing Deep Networks of Information
Accessible from Input-Output Observations
- Authors: Aditya Golatkar, Alessandro Achille, Stefano Soatto
- Abstract summary: We describe a procedure for removing dependency on a cohort of training data from a trained deep network.
We introduce a new bound on how much information can be extracted per query about the forgotten cohort.
We exploit the connections between the activation and weight dynamics of a DNN inspired by Neural Tangent Kernels to compute the information in the activations.
- Score: 143.3053365553897
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We describe a procedure for removing dependency on a cohort of training data
from a trained deep network that improves upon and generalizes previous methods
to different readout functions and can be extended to ensure forgetting in the
activations of the network. We introduce a new bound on how much information
can be extracted per query about the forgotten cohort from a black-box network
for which only the input-output behavior is observed. The proposed forgetting
procedure has a deterministic part derived from the differential equations of a
linearized version of the model, and a stochastic part that ensures information
destruction by adding noise tailored to the geometry of the loss landscape. We
exploit the connections between the activation and weight dynamics of a DNN
inspired by Neural Tangent Kernels to compute the information in the
activations.
Related papers
- Localized Gaussians as Self-Attention Weights for Point Clouds Correspondence [92.07601770031236]
We investigate semantically meaningful patterns in the attention heads of an encoder-only Transformer architecture.
We find that fixing the attention weights not only accelerates the training process but also enhances the stability of the optimization.
arXiv Detail & Related papers (2024-09-20T07:41:47Z) - Opening the Black Box: predicting the trainability of deep neural networks with reconstruction entropy [0.0]
We present a method for predicting the trainable regime in parameter space for deep feedforward neural networks.
For both the MNIST and CIFAR10 datasets, we show that a single epoch of training is sufficient to predict the trainability of the deep feedforward network.
arXiv Detail & Related papers (2024-06-13T18:00:05Z) - Network Inversion of Binarised Neural Nets [3.5571131514746837]
Network inversion plays a pivotal role in unraveling the black-box nature of input to output mappings in neural networks.
This paper introduces a novel approach to invert a trained BNN by encoding it into a CNF formula that captures the network's structure.
arXiv Detail & Related papers (2024-02-19T09:39:54Z) - STEERING: Stein Information Directed Exploration for Model-Based
Reinforcement Learning [111.75423966239092]
We propose an exploration incentive in terms of the integral probability metric (IPM) between a current estimate of the transition model and the unknown optimal.
Based on KSD, we develop a novel algorithm algo: textbfSTEin information dirtextbfEcted exploration for model-based textbfReinforcement LearntextbfING.
arXiv Detail & Related papers (2023-01-28T00:49:28Z) - Robust Explanation Constraints for Neural Networks [33.14373978947437]
Post-hoc explanation methods used with the intent of neural networks are sometimes said to help engender trust in their outputs.
Our training method is the only method able to learn neural networks with insights about robustness tested across all six tested networks.
arXiv Detail & Related papers (2022-12-16T14:40:25Z) - Information Removal at the bottleneck in Deep Neural Networks [3.1473798197405944]
We propose IRENE, a method to achieve information removal at the bottleneck of deep neural networks.
Experiments on a synthetic dataset and on CelebA validate the effectiveness of the proposed approach.
arXiv Detail & Related papers (2022-09-30T14:20:21Z) - Decomposing neural networks as mappings of correlation functions [57.52754806616669]
We study the mapping between probability distributions implemented by a deep feed-forward network.
We identify essential statistics in the data, as well as different information representations that can be used by neural networks.
arXiv Detail & Related papers (2022-02-10T09:30:31Z) - Mixed-Privacy Forgetting in Deep Networks [114.3840147070712]
We show that the influence of a subset of the training samples can be removed from the weights of a network trained on large-scale image classification tasks.
Inspired by real-world applications of forgetting techniques, we introduce a novel notion of forgetting in mixed-privacy setting.
We show that our method allows forgetting without having to trade off the model accuracy.
arXiv Detail & Related papers (2020-12-24T19:34:56Z) - Distillation of Weighted Automata from Recurrent Neural Networks using a
Spectral Approach [0.0]
This paper is an attempt to bridge the gap between deep learning and grammatical inference.
It provides an algorithm to extract a formal language from any recurrent neural network trained for language modelling.
arXiv Detail & Related papers (2020-09-28T07:04:15Z) - Focus of Attention Improves Information Transfer in Visual Features [80.22965663534556]
This paper focuses on unsupervised learning for transferring visual information in a truly online setting.
The computation of the entropy terms is carried out by a temporal process which yields online estimation of the entropy terms.
In order to better structure the input probability distribution, we use a human-like focus of attention model.
arXiv Detail & Related papers (2020-06-16T15:07:25Z)
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.