Knowledge Removal in Sampling-based Bayesian Inference

• URL: http://arxiv.org/abs/2203.12964v1
• Date: Thu, 24 Mar 2022 10:03:01 GMT
• Title: Knowledge Removal in Sampling-based Bayesian Inference
• Authors: Shaopeng Fu, Fengxiang He, Dacheng Tao
• Abstract summary: When single data deletion requests come, companies may need to delete the whole models learned with massive resources. Existing works propose methods to remove knowledge learned from data for explicitly parameterized models. In this paper, we propose the first machine unlearning algorithm for MCMC.
• Score: 86.14397783398711
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The right to be forgotten has been legislated in many countries, but its enforcement in the AI industry would cause unbearable costs. When single data deletion requests come, companies may need to delete the whole models learned with massive resources. Existing works propose methods to remove knowledge learned from data for explicitly parameterized models, which however are not appliable to the sampling-based Bayesian inference, i.e., Markov chain Monte Carlo (MCMC), as MCMC can only infer implicit distributions. In this paper, we propose the first machine unlearning algorithm for MCMC. We first convert the MCMC unlearning problem into an explicit optimization problem. Based on this problem conversion, an {\it MCMC influence function} is designed to provably characterize the learned knowledge from data, which then delivers the MCMC unlearning algorithm. Theoretical analysis shows that MCMC unlearning would not compromise the generalizability of the MCMC models. Experiments on Gaussian mixture models and Bayesian neural networks confirm the effectiveness of the proposed algorithm. The code is available at \url{https://github.com/fshp971/mcmc-unlearning}.

Related papers

• MCMC-driven learning [64.94438070592365]
  This paper is intended to appear as a chapter for the Handbook of Monte Carlo. The goal of this paper is to unify various problems at the intersection of Markov chain learning.
  arXiv  Detail & Related papers  (2024-02-14T22:10:42Z)
• Learning Energy-based Model via Dual-MCMC Teaching [5.31573596283377]
  Learning the energy-based model (EBM) can be achieved using the maximum likelihood estimation (MLE) This paper studies the fundamental learning problem of the energy-based model (EBM)
  arXiv  Detail & Related papers  (2023-12-05T03:39:54Z)
• Bayesian neural networks via MCMC: a Python-based tutorial [0.196629787330046]
  Variational inference and Markov Chain Monte-Carlo sampling methods are used to implement Bayesian inference. This tutorial provides code in Python with data and instructions that enable their use and extension.
  arXiv  Detail & Related papers  (2023-04-02T02:19:15Z)
• DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm [21.128416842467132]
  We derive a user-friendly centralised distributed MCMC algorithm with provable scaling in high-dimensional settings. We illustrate the relevance of the proposed methodology on both synthetic and real data experiments.
  arXiv  Detail & Related papers  (2021-06-11T10:37:14Z)
• Bayesian Inference Forgetting [82.6681466124663]
  The right to be forgotten has been legislated in many countries but the enforcement in machine learning would cause unbearable costs. This paper proposes a it Bayesian inference forgetting (BIF) framework to realize the right to be forgotten in Bayesian inference.
  arXiv  Detail & Related papers  (2021-01-16T09:52:51Z)
• Non-convex Learning via Replica Exchange Stochastic Gradient MCMC [25.47669573608621]
  We propose an adaptive replica exchange SGMCMC (reSGMCMC) to automatically correct the bias and study the corresponding properties. Empirically, we test the algorithm through extensive experiments on various setups and obtain the results.
  arXiv  Detail & Related papers  (2020-08-12T15:02:59Z)
• Involutive MCMC: a Unifying Framework [64.46316409766764]
  We describe a wide range of MCMC algorithms in terms of iMCMC. We formulate a number of "tricks" which one can use as design principles for developing new MCMC algorithms. We demonstrate the latter with two examples where we transform known reversible MCMC algorithms into more efficient irreversible ones.
  arXiv  Detail & Related papers  (2020-06-30T10:21:42Z)
• MMCGAN: Generative Adversarial Network with Explicit Manifold Prior [78.58159882218378]
  We propose to employ explicit manifold learning as prior to alleviate mode collapse and stabilize training of GAN. Our experiments on both the toy data and real datasets show the effectiveness of MMCGAN in alleviating mode collapse, stabilizing training, and improving the quality of generated samples.
  arXiv  Detail & Related papers  (2020-06-18T07:38:54Z)
• MCMC Should Mix: Learning Energy-Based Model with Neural Transport Latent Space MCMC [110.02001052791353]
  Learning energy-based model (EBM) requires MCMC sampling of the learned model as an inner loop of the learning algorithm. We show that the model has a particularly simple form in the space of the latent variables of the backbone model.
  arXiv  Detail & Related papers  (2020-06-12T01:25:51Z)

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.