Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning

• URL: http://arxiv.org/abs/2306.03364v4
• Date: Fri, 16 Feb 2024 17:08:51 GMT
• Title: Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning
• Authors: Nicolas Michel, Giovanni Chierchia, Romain Negrel, Jean-Fran\c{c}ois Bercher
• Abstract summary: We propose a memory-based representation learning technique equipped with our new loss functions. We demonstrate that the proposed method outperforms the current state-of-the-art methods on both standard evaluation scenarios and realistic scenarios with blurry task boundaries.
• Score: 7.145581090959242
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We use the maximum a posteriori estimation principle for learning representations distributed on the unit sphere. We propose to use the angular Gaussian distribution, which corresponds to a Gaussian projected on the unit-sphere and derive the associated loss function. We also consider the von Mises-Fisher distribution, which is the conditional of a Gaussian in the unit-sphere. The learned representations are pushed toward fixed directions, which are the prior means of the Gaussians; allowing for a learning strategy that is resilient to data drift. This makes it suitable for online continual learning, which is the problem of training neural networks on a continuous data stream, where multiple classification tasks are presented sequentially so that data from past tasks are no longer accessible, and data from the current task can be seen only once. To address this challenging scenario, we propose a memory-based representation learning technique equipped with our new loss functions. Our approach does not require negative data or knowledge of task boundaries and performs well with smaller batch sizes while being computationally efficient. We demonstrate with extensive experiments that the proposed method outperforms the current state-of-the-art methods on both standard evaluation scenarios and realistic scenarios with blurry task boundaries. For reproducibility, we use the same training pipeline for every compared method and share the code at https://github.com/Nicolas1203/ocl-fd.

Related papers

• Efficient Weight-Space Laplace-Gaussian Filtering and Smoothing for Sequential Deep Learning [29.328769628694484]
  Efficiently learning a sequence of related tasks, such as in continual learning, poses a significant challenge for neural nets. We address this challenge with a grounded framework for sequentially learning related tasks based on Bayesian inference.
  arXiv  Detail & Related papers  (2024-10-09T11:54:33Z)
• Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning [100.7407460674153]
  Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks. To mitigate the problem, a line of methods propose to replay the data of experienced tasks when learning new tasks. However, it is not expected in practice considering the memory constraint or data privacy issue. As a replacement, data-free data replay methods are proposed by inverting samples from the classification model.
  arXiv  Detail & Related papers  (2024-01-12T12:51:12Z)
• Kernel Density Bayesian Inverse Reinforcement Learning [5.699034783029326]
  Inverse reinforcement learning (IRL) methods infer an agent's reward function using demonstrations of expert behavior. This work introduces a principled and theoretically grounded framework that enables Bayesian IRL to be applied across a variety of domains.
  arXiv  Detail & Related papers  (2023-03-13T03:00:03Z)
• The Challenges of Continuous Self-Supervised Learning [40.941767578622745]
  Self-supervised learning (SSL) aims to eliminate one of the major bottlenecks in representation learning - the need for human annotations. We show that a direct application of current methods to such continuous setup is inefficient both computationally and in the amount of data required. We propose the use of replay buffers as an approach to alleviate the issues of inefficiency and temporal correlations.
  arXiv  Detail & Related papers  (2022-03-23T20:05:06Z)
• On Generalizing Beyond Domains in Cross-Domain Continual Learning [91.56748415975683]
  Deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task. Our proposed approach learns new tasks under domain shift with accuracy boosts up to 10% on challenging datasets such as DomainNet and OfficeHome.
  arXiv  Detail & Related papers  (2022-03-08T09:57:48Z)
• Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations [76.82124752950148]
  We develop a convenient gradient-based method for selecting the data augmentation. We use a differentiable Kronecker-factored Laplace approximation to the marginal likelihood as our objective.
  arXiv  Detail & Related papers  (2022-02-22T02:51:11Z)
• Transformers Can Do Bayesian Inference [56.99390658880008]
  We present Prior-Data Fitted Networks (PFNs) PFNs leverage in-context learning in large-scale machine learning techniques to approximate a large set of posteriors. We demonstrate that PFNs can near-perfectly mimic Gaussian processes and also enable efficient Bayesian inference for intractable problems.
  arXiv  Detail & Related papers  (2021-12-20T13:07:39Z)
• Convolutional generative adversarial imputation networks for spatio-temporal missing data in storm surge simulations [86.5302150777089]
  Generative Adversarial Imputation Nets (GANs) and GAN-based techniques have attracted attention as unsupervised machine learning methods. We name our proposed method as Con Conval Generative Adversarial Imputation Nets (Conv-GAIN)
  arXiv  Detail & Related papers  (2021-11-03T03:50:48Z)
• Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates [28.662887957256913]
  Catastrophic forgetting is the notorious vulnerability of neural networks to the changes in the data distribution during learning. We derive novel fixed-point equations for the online variational Bayes optimization problem. We obtain an algorithm (FOO-VB) for continual learning which can handle non-stationary data distribution.
  arXiv  Detail & Related papers  (2020-10-01T13:10:35Z)
• DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction [96.90215318875859]
  We show that bootstrapping-based Q-learning algorithms do not necessarily benefit from corrective feedback. We propose a new algorithm, DisCor, which computes an approximation to this optimal distribution and uses it to re-weight the transitions used for training.
  arXiv  Detail & Related papers  (2020-03-16T16:18:52Z)

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.