Function-space Parameterization of Neural Networks for Sequential Learning

• URL: http://arxiv.org/abs/2403.10929v1
• Date: Sat, 16 Mar 2024 14:00:04 GMT
• Title: Function-space Parameterization of Neural Networks for Sequential Learning
• Authors: Aidan Scannell, Riccardo Mereu, Paul Chang, Ella Tamir, Joni Pajarinen, Arno Solin,
• Abstract summary: Sequential learning paradigms pose challenges for gradient-based deep learning due to difficulties incorporating new data and retaining prior knowledge. We introduce a technique that converts neural networks from weight space to function space, through a dual parameterization. Our experiments demonstrate that we can retain knowledge in continual learning and incorporate new data efficiently.
• Score: 22.095632118886225
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sequential learning paradigms pose challenges for gradient-based deep learning due to difficulties incorporating new data and retaining prior knowledge. While Gaussian processes elegantly tackle these problems, they struggle with scalability and handling rich inputs, such as images. To address these issues, we introduce a technique that converts neural networks from weight space to function space, through a dual parameterization. Our parameterization offers: (i) a way to scale function-space methods to large data sets via sparsification, (ii) retention of prior knowledge when access to past data is limited, and (iii) a mechanism to incorporate new data without retraining. Our experiments demonstrate that we can retain knowledge in continual learning and incorporate new data efficiently. We further show its strengths in uncertainty quantification and guiding exploration in model-based RL. Further information and code is available on the project website.

Related papers

• 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)
• Learning of networked spreading models from noisy and incomplete data [7.669018800404791]
  We introduce a universal learning method based on scalable dynamic message-passing technique. The algorithm leverages available prior knowledge on the model and on the data, and reconstructs both network structure and parameters of a spreading model. We show that a linear computational complexity of the method with the key model parameters makes the algorithm scalable to large network instances.
  arXiv  Detail & Related papers  (2023-12-20T13:12:47Z)
• Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection [56.292071534857946]
  Recent data-privacy laws have sparked interest in machine unlearning. Challenge is to discard information about the forget'' data without altering knowledge about remaining dataset. We adopt a projected-gradient based learning method, named as Projected-Gradient Unlearning (PGU) We provide empirically evidence to demonstrate that our unlearning method can produce models that behave similar to models retrained from scratch across various metrics even when the training dataset is no longer accessible.
  arXiv  Detail & Related papers  (2023-12-07T07:17:24Z)
• Data Augmentations in Deep Weight Spaces [89.45272760013928]
  We introduce a novel augmentation scheme based on the Mixup method. We evaluate the performance of these techniques on existing benchmarks as well as new benchmarks we generate.
  arXiv  Detail & Related papers  (2023-11-15T10:43:13Z)
• ShadowNet for Data-Centric Quantum System Learning [188.683909185536]
  We propose a data-centric learning paradigm combining the strength of neural-network protocols and classical shadows. Capitalizing on the generalization power of neural networks, this paradigm can be trained offline and excel at predicting previously unseen systems. We present the instantiation of our paradigm in quantum state tomography and direct fidelity estimation tasks and conduct numerical analysis up to 60 qubits.
  arXiv  Detail & Related papers  (2023-08-22T09:11:53Z)
• Subspace Distillation for Continual Learning [27.22147868163214]
  We propose a knowledge distillation technique that takes into account the manifold structure of a neural network in learning novel tasks. We demonstrate that the modeling with subspaces provides several intriguing properties, including robustness to noise. Empirically, we observe that our proposed method outperforms various continual learning methods on several challenging datasets.
  arXiv  Detail & Related papers  (2023-07-31T05:59:09Z)
• Complementary Learning Subnetworks for Parameter-Efficient Class-Incremental Learning [40.13416912075668]
  We propose a rehearsal-free CIL approach that learns continually via the synergy between two Complementary Learning Subnetworks. Our method achieves competitive results against state-of-the-art methods, especially in accuracy gain, memory cost, training efficiency, and task-order.
  arXiv  Detail & Related papers  (2023-06-21T01:43:25Z)
• PIVOT: Prompting for Video Continual Learning [50.80141083993668]
  We introduce PIVOT, a novel method that leverages extensive knowledge in pre-trained models from the image domain. Our experiments show that PIVOT improves state-of-the-art methods by a significant 27% on the 20-task ActivityNet setup.
  arXiv  Detail & Related papers  (2022-12-09T13:22:27Z)
• Online Deep Learning from Doubly-Streaming Data [17.119725174036653]
  This paper investigates a new online learning problem with doubly-streaming data, where the data streams are described by feature spaces that constantly evolve. A plausible idea to overcome the challenges is to establish relationship between the pre-and-post evolving feature spaces. We propose a novel OLD3S paradigm, where a shared latent subspace is discovered to summarize information from the old and new feature spaces.
  arXiv  Detail & Related papers  (2022-04-25T17:06:39Z)
• Neural Galerkin Schemes with Active Learning for High-Dimensional Evolution Equations [44.89798007370551]
  This work proposes Neural Galerkin schemes based on deep learning that generate training data with active learning for numerically solving high-dimensional partial differential equations. Neural Galerkin schemes build on the Dirac-Frenkel variational principle to train networks by minimizing the residual sequentially over time. Our finding is that the active form of gathering training data of the proposed Neural Galerkin schemes is key for numerically realizing the expressive power of networks in high dimensions.
  arXiv  Detail & Related papers  (2022-03-02T19:09:52Z)
• Continual Learning via Bit-Level Information Preserving [88.32450740325005]
  We study the continual learning process through the lens of information theory. We propose Bit-Level Information Preserving (BLIP) that preserves the information gain on model parameters. BLIP achieves close to zero forgetting while only requiring constant memory overheads throughout continual learning.
  arXiv  Detail & Related papers  (2021-05-10T15:09:01Z)

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.