Continual Learning of Generative Models with Limited Data: From Wasserstein-1 Barycenter to Adaptive Coalescence

• URL: http://arxiv.org/abs/2101.09225v1
• Date: Fri, 22 Jan 2021 17:15:39 GMT
• Title: Continual Learning of Generative Models with Limited Data: From Wasserstein-1 Barycenter to Adaptive Coalescence
• Authors: Mehmet Dedeoglu, Sen Lin, Zhaofeng Zhang, Junshan Zhang
• Abstract summary: Learning generative models is challenging for a network edge node with limited data and computing power. This study aims to develop a framework which systematically optimize continual learning of generative models.
• Score: 22.82926450287203
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning generative models is challenging for a network edge node with limited data and computing power. Since tasks in similar environments share model similarity, it is plausible to leverage pre-trained generative models from the cloud or other edge nodes. Appealing to optimal transport theory tailored towards Wasserstein-1 generative adversarial networks (WGAN), this study aims to develop a framework which systematically optimizes continual learning of generative models using local data at the edge node while exploiting adaptive coalescence of pre-trained generative models. Specifically, by treating the knowledge transfer from other nodes as Wasserstein balls centered around their pre-trained models, continual learning of generative models is cast as a constrained optimization problem, which is further reduced to a Wasserstein-1 barycenter problem. A two-stage approach is devised accordingly: 1) The barycenters among the pre-trained models are computed offline, where displacement interpolation is used as the theoretic foundation for finding adaptive barycenters via a "recursive" WGAN configuration; 2) the barycenter computed offline is used as meta-model initialization for continual learning and then fast adaptation is carried out to find the generative model using the local samples at the target edge node. Finally, a weight ternarization method, based on joint optimization of weights and threshold for quantization, is developed to compress the generative model further.

Related papers

• A model-constrained Discontinuous Galerkin Network (DGNet) for Compressible Euler Equations with Out-of-Distribution Generalization [0.0]
  We develop a model-constrained discontinuous Galerkin Network (DGNet) approach to solve compressible Euler equations. To validate the effectiveness, stability, and generalizability of our novel DGNet approach, we present numerical results for 1D and 2D compressible Euler equation problems.
  arXiv  Detail & Related papers  (2024-09-27T01:13:38Z)
• Diffusion-Based Neural Network Weights Generation [80.89706112736353]
  D2NWG is a diffusion-based neural network weights generation technique that efficiently produces high-performing weights for transfer learning. Our method extends generative hyper-representation learning to recast the latent diffusion paradigm for neural network weights generation. Our approach is scalable to large architectures such as large language models (LLMs), overcoming the limitations of current parameter generation techniques.
  arXiv  Detail & Related papers  (2024-02-28T08:34:23Z)
• Towards Continual Learning Desiderata via HSIC-Bottleneck Orthogonalization and Equiangular Embedding [55.107555305760954]
  We propose a conceptually simple yet effective method that attributes forgetting to layer-wise parameter overwriting and the resulting decision boundary distortion. Our method achieves competitive accuracy performance, even with absolute superiority of zero exemplar buffer and 1.02x the base model.
  arXiv  Detail & Related papers  (2024-01-17T09:01:29Z)
• Federated Learning with Projected Trajectory Regularization [65.6266768678291]
  Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients. We propose a novel federated learning framework with projected trajectory regularization (FedPTR) for tackling the data issue.
  arXiv  Detail & Related papers  (2023-12-22T02:12:08Z)
• Diffusion-Model-Assisted Supervised Learning of Generative Models for Density Estimation [10.793646707711442]
  We present a framework for training generative models for density estimation. We use the score-based diffusion model to generate labeled data. Once the labeled data are generated, we can train a simple fully connected neural network to learn the generative model in the supervised manner.
  arXiv  Detail & Related papers  (2023-10-22T23:56:19Z)
• Dual Student Networks for Data-Free Model Stealing [79.67498803845059]
  Two main challenges are estimating gradients of the target model without access to its parameters, and generating a diverse set of training samples. We propose a Dual Student method where two students are symmetrically trained in order to provide the generator a criterion to generate samples that the two students disagree on. We show that our new optimization framework provides more accurate gradient estimation of the target model and better accuracies on benchmark classification datasets.
  arXiv  Detail & Related papers  (2023-09-18T18:11:31Z)
• A Deep Dive into the Connections Between the Renormalization Group and Deep Learning in the Ising Model [0.0]
  Renormalization group (RG) is an essential technique in statistical physics and quantum field theory. We develop extensive renormalization techniques for the 1D and 2D Ising model to provide a baseline for comparison. For the 2D Ising model, we successfully generated Ising model samples using the Wolff algorithm, and performed the group flow using a quasi-deterministic method.
  arXiv  Detail & Related papers  (2023-08-21T22:50:54Z)
• Towards a Better Theoretical Understanding of Independent Subnetwork Training [56.24689348875711]
  We take a closer theoretical look at Independent Subnetwork Training (IST) IST is a recently proposed and highly effective technique for solving the aforementioned problems. We identify fundamental differences between IST and alternative approaches, such as distributed methods with compressed communication.
  arXiv  Detail & Related papers  (2023-06-28T18:14:22Z)
• TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization [89.54947228958494]
  This paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks. We propose a novel statistics-based approach, Two-WIng NormliSation (TWINS) fine-tuning framework. TWINS is shown to be effective on a wide range of image classification datasets in terms of both generalization and robustness.
  arXiv  Detail & Related papers  (2023-03-20T14:12:55Z)
• Sparsely constrained neural networks for model discovery of PDEs [0.0]
  We present a modular framework that determines the sparsity pattern of a deep-learning based surrogate using any sparse regression technique. We show how a different network architecture and sparsity estimator improve model discovery accuracy and convergence on several benchmark examples.
  arXiv  Detail & Related papers  (2020-11-09T11:02:40Z)
• Learning Generative Models using Denoising Density Estimators [29.068491722778827]
  We introduce a new generative model based on denoising density estimators (DDEs) Our main contribution is a novel technique to obtain generative models by minimizing the KL-divergence directly. Experimental results demonstrate substantial improvement in density estimation and competitive performance in generative model training.
  arXiv  Detail & Related papers  (2020-01-08T20:30:40Z)

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.