Unifying Regularisation Methods for Continual Learning

• URL: http://arxiv.org/abs/2006.06357v2
• Date: Wed, 3 Feb 2021 20:53:03 GMT
• Title: Unifying Regularisation Methods for Continual Learning
• Authors: Frederik Benzing
• Abstract summary: Continual Learning addresses the challenge of learning a number of different tasks sequentially. The goal of maintaining knowledge of earlier tasks without re-accessing them starkly conflicts with standard SGD training for artificial neural networks. Regularisation approaches measure the importance of each parameter for solving a given task and protect important parameters from large changes.
• Score: 0.913755431537592
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual Learning addresses the challenge of learning a number of different tasks sequentially. The goal of maintaining knowledge of earlier tasks without re-accessing them starkly conflicts with standard SGD training for artificial neural networks. An influential method to tackle this problem without storing old data are so-called regularisation approaches. They measure the importance of each parameter for solving a given task and subsequently protect important parameters from large changes. In the literature, three ways to measure parameter importance have been put forward and they have inspired a large body of follow-up work. Here, we present strong theoretical and empirical evidence that these three methods, Elastic Weight Consolidation (EWC), Synaptic Intelligence (SI) and Memory Aware Synapses (MAS), are surprisingly similar and are all linked to the same theoretical quantity. Concretely, we show that, despite stemming from very different motivations, both SI and MAS approximate the square root of the Fisher Information, with the Fisher being the theoretically justified basis of EWC. Moreover, we show that for SI the relation to the Fisher -- and in fact its performance -- is due to a previously unknown bias. On top of uncovering unknown similarities and unifying regularisation approaches, we also demonstrate that our insights enable practical performance improvements for large batch training.

Related papers

• Revisiting Bisimulation Metric for Robust Representations in Reinforcement Learning [7.2951508303962385]
  We identify two main issues with the conventional bisimulation metric.<n>We propose a revised bisimulation metric that features a more precise definition of reward gap and novel update operators with adaptive coefficient.
  arXiv  Detail & Related papers  (2025-07-24T15:42:22Z)
• EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental Learning [53.88000987041739]
  Class-Incremental Learning (CIL) aims to enable AI models to continuously learn from sequentially arriving data of different classes over time.<n>We propose the Elastic Knowledge Preservation and Compensation (EKPC) method, integrating Importance-aware importance Regularization (IPR) and Trainable Semantic Drift Compensation (TSDC) for CIL.
  arXiv  Detail & Related papers  (2025-06-14T05:19:58Z)
• Temporal-Difference Variational Continual Learning [89.32940051152782]
  A crucial capability of Machine Learning models in real-world applications is the ability to continuously learn new tasks. In Continual Learning settings, models often struggle to balance learning new tasks with retaining previous knowledge. We propose new learning objectives that integrate the regularization effects of multiple previous posterior estimations.
  arXiv  Detail & Related papers  (2024-10-10T10:58:41Z)
• Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs [63.36637269634553]
  We introduce a novel approach where LLMs are fine-tuned to generate a sequence of Diverse Chains of Thought (DCoT) within a single inference step.<n>We show that fine-tuning on DCoT improves performance over the CoT baseline across model families and scales.<n>Our work is also significant because both quantitative analyses and manual evaluations reveal the observed gains stem from the models' ability to refine an initial reasoning chain.
  arXiv  Detail & Related papers  (2024-07-03T15:01:18Z)
• MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset [50.36095192314595]
  Large Language Models (LLMs) function as conscious agents with generalizable reasoning capabilities. This ability remains underexplored due to the complexity of modeling infinite possible changes in an event. We introduce the first-ever benchmark, MARS, comprising three tasks corresponding to each step.
  arXiv  Detail & Related papers  (2024-06-04T08:35:04Z)
• Understanding Forgetting in Continual Learning with Linear Regression [21.8755265936716]
  Continual learning, focused on sequentially learning multiple tasks, has gained significant attention recently. We provide a general theoretical analysis of forgetting in the linear regression model via Gradient Descent. We demonstrate that, given a sufficiently large data size, the arrangement of tasks in a sequence, where tasks with larger eigenvalues in their population data covariance matrices are trained later, tends to result in increased forgetting.
  arXiv  Detail & Related papers  (2024-05-27T18:33:37Z)
• Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective [106.92016199403042]
  We empirically investigate knowledge transfer from larger to smaller models through a parametric perspective. We employ sensitivity-based techniques to extract and align knowledge-specific parameters between different large language models. Our findings highlight the critical factors contributing to the process of parametric knowledge transfer.
  arXiv  Detail & Related papers  (2023-10-17T17:58:34Z)
• Uncertainty Estimation by Fisher Information-based Evidential Deep Learning [61.94125052118442]
  Uncertainty estimation is a key factor that makes deep learning reliable in practical applications. We propose a novel method, Fisher Information-based Evidential Deep Learning ($mathcalI$-EDL) In particular, we introduce Fisher Information Matrix (FIM) to measure the informativeness of evidence carried by each sample, according to which we can dynamically reweight the objective loss terms to make the network more focused on the representation learning of uncertain classes.
  arXiv  Detail & Related papers  (2023-03-03T16:12:59Z)
• Automatic Data Augmentation via Invariance-Constrained Learning [94.27081585149836]
  Underlying data structures are often exploited to improve the solution of learning tasks. Data augmentation induces these symmetries during training by applying multiple transformations to the input data. This work tackles these issues by automatically adapting the data augmentation while solving the learning task.
  arXiv  Detail & Related papers  (2022-09-29T18:11:01Z)
• Rethinking Bayesian Learning for Data Analysis: The Art of Prior and Inference in Sparsity-Aware Modeling [20.296566563098057]
  Sparse modeling for signal processing and machine learning has been at the focus of scientific research for over two decades. This article reviews some recent advances in incorporating sparsity-promoting priors into three popular data modeling tools.
  arXiv  Detail & Related papers  (2022-05-28T00:43:52Z)
• Differential Privacy and Byzantine Resilience in SGD: Do They Add Up? [6.614755043607777]
  We study whether a distributed implementation of the renowned Gradient Descent (SGD) learning algorithm is feasible with both differential privacy (DP) and $(alpha,f)$-Byzantine resilience. We show that a direct composition of these techniques makes the guarantees of the resulting SGD algorithm depend unfavourably upon the number of parameters in the ML model.
  arXiv  Detail & Related papers  (2021-02-16T14:10:38Z)
• Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint [35.5156045701898]
  We provide a novel viewpoint of regularization-based continual learning by formulating it as a second-order Taylor approximation of the loss function of each task. Based on this viewpoint, we study the optimization aspects (i.e., convergence) as well as generalization properties (i.e., finite-sample guarantees) of regularization-based continual learning.
  arXiv  Detail & Related papers  (2020-06-19T06:08:40Z)
• Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors [75.58555462743585]
  Naively trained neural networks tend to experience catastrophic forgetting in sequential task settings. We propose a principled nonparametric approach based on the Indian Buffet Process (IBP) prior, letting the data determine how much to expand the model complexity. We demonstrate the effectiveness of our method on a number of continual learning benchmarks and analyze how weight factors are allocated and reused throughout the training.
  arXiv  Detail & Related papers  (2020-04-21T15:20:19Z)

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.