Efficient Continual Learning with Modular Networks and Task-Driven Priors

• URL: http://arxiv.org/abs/2012.12631v2
• Date: Fri, 12 Feb 2021 18:25:43 GMT
• Title: Efficient Continual Learning with Modular Networks and Task-Driven Priors
• Authors: Tom Veniat and Ludovic Denoyer and Marc'Aurelio Ranzato
• Abstract summary: Existing literature in Continual Learning (CL) has focused on overcoming catastrophic forgetting. We introduce a new modular architecture, whose modules represent atomic skills that can be composed to perform a certain task. Our learning algorithm leverages a task-driven prior over the exponential search space of all possible ways to combine modules, enabling efficient learning on long streams of tasks.
• Score: 31.03712334701338
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing literature in Continual Learning (CL) has focused on overcoming catastrophic forgetting, the inability of the learner to recall how to perform tasks observed in the past. There are however other desirable properties of a CL system, such as the ability to transfer knowledge from previous tasks and to scale memory and compute sub-linearly with the number of tasks. Since most current benchmarks focus only on forgetting using short streams of tasks, we first propose a new suite of benchmarks to probe CL algorithms across these new axes. Finally, we introduce a new modular architecture, whose modules represent atomic skills that can be composed to perform a certain task. Learning a task reduces to figuring out which past modules to re-use, and which new modules to instantiate to solve the current task. Our learning algorithm leverages a task-driven prior over the exponential search space of all possible ways to combine modules, enabling efficient learning on long streams of tasks. Our experiments show that this modular architecture and learning algorithm perform competitively on widely used CL benchmarks while yielding superior performance on the more challenging benchmarks we introduce in this work.

Related papers

• Slowing Down Forgetting in Continual Learning [20.57872238271025]
  A common challenge in continual learning (CL) is forgetting, where the performance on old tasks drops after new, additional tasks are learned. We propose a novel framework called ReCL to slow down forgetting in CL.
  arXiv  Detail & Related papers  (2024-11-11T12:19:28Z)
• Continual Referring Expression Comprehension via Dual Modular Memorization [133.46886428655426]
  Referring Expression (REC) aims to localize an image region of a given object described by a natural-language expression. Existing REC algorithms make a strong assumption that training data feeding into a model are given upfront, which degrades its practicality for real-world scenarios. In this paper, we propose Continual Referring Expression (CREC), a new setting for REC, where a model is learning on a stream of incoming tasks. In order to continuously improve the model on sequential tasks without forgetting prior learned knowledge and without repeatedly re-training from a scratch, we propose an effective baseline method named Dual Modular Memorization
  arXiv  Detail & Related papers  (2023-11-25T02:58:51Z)
• LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning [64.55001982176226]
  LIBERO is a novel benchmark of lifelong learning for robot manipulation. We focus on how to efficiently transfer declarative knowledge, procedural knowledge, or the mixture of both. We develop an extendible procedural generation pipeline that can in principle generate infinitely many tasks.
  arXiv  Detail & Related papers  (2023-06-05T23:32:26Z)
• Continual Learning via Learning a Continual Memory in Vision Transformer [7.116223171323158]
  We study task-incremental continual learning (TCL) using Vision Transformers (ViTs) Our goal is to improve the overall streaming-task performance without catastrophic forgetting by learning task synergies. We present a Hierarchical task-synergy Exploration-Exploitation (HEE) sampling based neural architecture search (NAS) method for effectively learning task synergies.
  arXiv  Detail & Related papers  (2023-03-14T21:52:27Z)
• Neural Weight Search for Scalable Task Incremental Learning [6.413209417643468]
  Task incremental learning aims to enable a system to maintain its performance on previously learned tasks while learning new tasks, solving the problem of catastrophic forgetting. One promising approach is to build an individual network or sub-network for future tasks. This leads to an ever-growing memory due to saving extra weights for new tasks and how to address this issue has remained an open problem in task incremental learning.
  arXiv  Detail & Related papers  (2022-11-24T23:30:23Z)
• Task Residual for Tuning Vision-Language Models [69.22958802711017]
  We propose a new efficient tuning approach for vision-language models (VLMs) named Task Residual Tuning (TaskRes) TaskRes explicitly decouples the prior knowledge of the pre-trained models and new knowledge regarding a target task. The proposed TaskRes is simple yet effective, which significantly outperforms previous methods on 11 benchmark datasets.
  arXiv  Detail & Related papers  (2022-11-18T15:09:03Z)
• Toward Sustainable Continual Learning: Detection and Knowledge Repurposing of Similar Tasks [31.095642850920385]
  We introduce a paradigm where the continual learner gets a sequence of mixed similar and dissimilar tasks. We propose a new continual learning framework that uses a task similarity detection function that does not require additional learning. Our experiments show that the proposed framework performs competitively on widely used computer vision benchmarks.
  arXiv  Detail & Related papers  (2022-10-11T19:35:30Z)
• Effects of Auxiliary Knowledge on Continual Learning [16.84113206569365]
  In Continual Learning (CL), a neural network is trained on a stream of data whose distribution changes over time. Most existing CL approaches focus on finding solutions to preserve acquired knowledge, so working on the past of the model. We argue that as the model has to continually learn new tasks, it is also important to put focus on the present knowledge that could improve following tasks learning.
  arXiv  Detail & Related papers  (2022-06-03T14:31:59Z)
• Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks [59.12108527904171]
  A model should recognize new classes and maintain discriminability over old classes. The task of recognizing few-shot new classes without forgetting old classes is called few-shot class-incremental learning (FSCIL) We propose a new paradigm for FSCIL based on meta-learning by LearnIng Multi-phase Incremental Tasks (LIMIT)
  arXiv  Detail & Related papers  (2022-03-31T13:46:41Z)
• vCLIMB: A Novel Video Class Incremental Learning Benchmark [53.90485760679411]
  We introduce vCLIMB, a novel video continual learning benchmark. vCLIMB is a standardized test-bed to analyze catastrophic forgetting of deep models in video continual learning. We propose a temporal consistency regularization that can be applied on top of memory-based continual learning methods.
  arXiv  Detail & Related papers  (2022-01-23T22:14:17Z)
• Bilevel Continual Learning [76.50127663309604]
  We present a novel framework of continual learning named "Bilevel Continual Learning" (BCL) Our experiments on continual learning benchmarks demonstrate the efficacy of the proposed BCL compared to many state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-30T16:00:23Z)

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.