Tuned Compositional Feature Replays for Efficient Stream Learning

• URL: http://arxiv.org/abs/2104.02206v8
• Date: Tue, 2 Jan 2024 16:12:32 GMT
• Title: Tuned Compositional Feature Replays for Efficient Stream Learning
• Authors: Morgan B. Talbot, Rushikesh Zawar, Rohil Badkundri, Mengmi Zhang, Gabriel Kreiman
• Abstract summary: We propose a new continual learning algorithm, Compositional Replay Using Memory Blocks (CRUMB) CRUMB mitigates forgetting by replaying feature maps reconstructed by combining generic parts. We stress-tested CRUMB alongside 13 competing methods on 7 challenging datasets.
• Score: 11.697781095636147
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Our brains extract durable, generalizable knowledge from transient experiences of the world. Artificial neural networks come nowhere close to this ability. When tasked with learning to classify objects by training on non-repeating video frames in temporal order (online stream learning), models that learn well from shuffled datasets catastrophically forget old knowledge upon learning new stimuli. We propose a new continual learning algorithm, Compositional Replay Using Memory Blocks (CRUMB), which mitigates forgetting by replaying feature maps reconstructed by combining generic parts. CRUMB concatenates trainable and re-usable "memory block" vectors to compositionally reconstruct feature map tensors in convolutional neural networks. Storing the indices of memory blocks used to reconstruct new stimuli enables memories of the stimuli to be replayed during later tasks. This reconstruction mechanism also primes the neural network to minimize catastrophic forgetting by biasing it towards attending to information about object shapes more than information about image textures, and stabilizes the network during stream learning by providing a shared feature-level basis for all training examples. These properties allow CRUMB to outperform an otherwise identical algorithm that stores and replays raw images, while occupying only 3.6% as much memory. We stress-tested CRUMB alongside 13 competing methods on 7 challenging datasets. To address the limited number of existing online stream learning datasets, we introduce 2 new benchmarks by adapting existing datasets for stream learning. With only 3.7-4.1% as much memory and 15-43% as much runtime, CRUMB mitigates catastrophic forgetting more effectively than the state-of-the-art. Our code is available at https://github.com/MorganBDT/crumb.git.

Related papers

• Look At Me, No Replay! SurpriseNet: Anomaly Detection Inspired Class Incremental Learning [14.529164755845688]
  Continual learning aims to create artificial neural networks capable of accumulating knowledge and skills through incremental training on a sequence of tasks. The main challenge of continual learning is catastrophic interference, wherein new knowledge overrides or interferes with past knowledge, leading to forgetting. A proposed solution, SurpriseNet, addresses catastrophic interference by employing a parameter isolation method and learning cross-task knowledge using an auto-encoder inspired by anomaly detection.
  arXiv  Detail & Related papers  (2023-10-30T22:16:26Z)
• Just a Glimpse: Rethinking Temporal Information for Video Continual Learning [58.7097258722291]
  We propose a novel replay mechanism for effective video continual learning based on individual/single frames. Under extreme memory constraints, video diversity plays a more significant role than temporal information. Our method achieves state-of-the-art performance, outperforming the previous state-of-the-art by up to 21.49%.
  arXiv  Detail & Related papers  (2023-05-28T19:14:25Z)
• Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning [54.7584721943286]
  Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. We propose to only activate and select sparse neurons for learning current and past tasks at any stage.
  arXiv  Detail & Related papers  (2022-02-21T13:25:03Z)
• Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings [89.63764845984076]
  We present Stored Embeddings for Efficient Reinforcement Learning (SEER) SEER is a simple modification of existing off-policy deep reinforcement learning methods. We show that SEER does not degrade the performance of RLizable agents while significantly saving computation and memory.
  arXiv  Detail & Related papers  (2021-03-04T08:14:10Z)
• EEC: Learning to Encode and Regenerate Images for Continual Learning [9.89901717499058]
  We train autoencoders with Neural Style Transfer to encode and store images. reconstructed images from encoded episodes are replayed in order to avoid catastrophic forgetting. Our approach increases classification accuracy by 13-17% over state-of-the-art methods on benchmark datasets.
  arXiv  Detail & Related papers  (2021-01-13T06:43:10Z)
• Knowledge Capture and Replay for Continual Learning [0.4980584790669266]
  We introduce em flashcards, which are visual representations that em capture encoded knowledge of a network. In a continual learning scenario, flashcards help to prevent forgetting and consolidating knowledge of all the previous tasks. We demonstrate the efficacy of flashcards in capturing learned knowledge representation (as an alternative to the original dataset) and empirically validate on a variety of continual learning tasks.
  arXiv  Detail & Related papers  (2020-12-12T11:24:45Z)
• Incremental Training of a Recurrent Neural Network Exploiting a Multi-Scale Dynamic Memory [79.42778415729475]
  We propose a novel incrementally trained recurrent architecture targeting explicitly multi-scale learning. We show how to extend the architecture of a simple RNN by separating its hidden state into different modules. We discuss a training algorithm where new modules are iteratively added to the model to learn progressively longer dependencies.
  arXiv  Detail & Related papers  (2020-06-29T08:35:49Z)
• Storing Encoded Episodes as Concepts for Continual Learning [22.387008072671005]
  Two main challenges faced by continual learning approaches are catastrophic forgetting and memory limitations on the storage of data. We propose a cognitively-inspired approach which trains autoencoders with Neural Style Transfer to encode and store images. Our approach increases classification accuracy by 13-17% over state-of-the-art methods on benchmark datasets, while requiring 78% less storage space.
  arXiv  Detail & Related papers  (2020-06-26T04:15:56Z)
• Neural Sparse Representation for Image Restoration [116.72107034624344]
  Inspired by the robustness and efficiency of sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks. Our method structurally enforces sparsity constraints upon hidden neurons. Experiments show that sparse representation is crucial in deep neural networks for multiple image restoration tasks.
  arXiv  Detail & Related papers  (2020-06-08T05:15:17Z)
• Encoding-based Memory Modules for Recurrent Neural Networks [79.42778415729475]
  We study the memorization subtask from the point of view of the design and training of recurrent neural networks. We propose a new model, the Linear Memory Network, which features an encoding-based memorization component built with a linear autoencoder for sequences.
  arXiv  Detail & Related papers  (2020-01-31T11:14:27Z)

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.