Related papers: Bilevel Continual Learning

Bilevel Continual Learning

URL: http://arxiv.org/abs/2007.15553v1
Date: Thu, 30 Jul 2020 16:00:23 GMT
Title: Bilevel Continual Learning
Authors: Quang Pham, Doyen Sahoo, Chenghao Liu, Steven C.H Hoi
Abstract summary: 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.
Score: 76.50127663309604
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Continual learning aims to learn continuously from a stream of tasks and data in an online-learning fashion, being capable of exploiting what was learned previously to improve current and future tasks while still being able to perform well on the previous tasks. One common limitation of many existing continual learning methods is that they often train a model directly on all available training data without validation due to the nature of continual learning, thus suffering poor generalization at test time. In this work, we present a novel framework of continual learning named "Bilevel Continual Learning" (BCL) by unifying a {\it bilevel optimization} objective and a {\it dual memory management} strategy comprising both episodic memory and generalization memory to achieve effective knowledge transfer to future tasks and alleviate catastrophic forgetting on old tasks simultaneously. Our extensive experiments on continual learning benchmarks demonstrate the efficacy of the proposed BCL compared to many state-of-the-art methods. Our implementation is available at https://github.com/phquang/bilevel-continual-learning.

Related papers

A Unified Framework for Continual Learning and Machine Unlearning [9.538733681436836]
Continual learning and machine unlearning are crucial challenges in machine learning, typically addressed separately. We introduce a novel framework that jointly tackles both tasks by leveraging controlled knowledge distillation. Our approach enables efficient learning with minimal forgetting and effective targeted unlearning.
arXiv Detail & Related papers (2024-08-21T06:49:59Z)
Learning to Learn for Few-shot Continual Active Learning [9.283518682371756]
Continual learning strives to ensure stability in solving previously seen tasks while demonstrating plasticity in a novel domain. Recent advances in continual learning are mostly confined to a supervised learning setting, especially in NLP domain. We exploit meta-learning and propose a method, called Meta-Continual Active Learning.
arXiv Detail & Related papers (2023-11-07T05:22:11Z)
Online Continual Learning via the Knowledge Invariant and Spread-out Properties [4.109784267309124]
Key challenge in continual learning is catastrophic forgetting. We propose a new method, named Online Continual Learning via the Knowledge Invariant and Spread-out Properties (OCLKISP) We empirically evaluate our proposed method on four popular benchmarks for continual learning: Split CIFAR 100, Split SVHN, Split CUB200 and Split Tiny-Image-Net.
arXiv Detail & Related papers (2023-02-02T04:03:38Z)
Continual Prompt Tuning for Dialog State Tracking [58.66412648276873]
A desirable dialog system should be able to continually learn new skills without forgetting old ones. We present Continual Prompt Tuning, a parameter-efficient framework that not only avoids forgetting but also enables knowledge transfer between tasks.
arXiv Detail & Related papers (2022-03-13T13:22:41Z)
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)
Relational Experience Replay: Continual Learning by Adaptively Tuning Task-wise Relationship [54.73817402934303]
We propose Experience Continual Replay (ERR), a bi-level learning framework to adaptively tune task-wise to achieve a better stability plasticity' tradeoff. ERR can consistently improve the performance of all baselines and surpass current state-of-the-art methods.
arXiv Detail & Related papers (2021-12-31T12:05:22Z)
Online Continual Learning with Natural Distribution Shifts: An Empirical Study with Visual Data [101.6195176510611]
"Online" continual learning enables evaluating both information retention and online learning efficacy. In online continual learning, each incoming small batch of data is first used for testing and then added to the training set, making the problem truly online. We introduce a new benchmark for online continual visual learning that exhibits large scale and natural distribution shifts.
arXiv Detail & Related papers (2021-08-20T06:17:20Z)
Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning [74.07455280246212]
Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. We show that current continual learning, meta-learning, meta-continual learning, and continual-meta learning techniques fail in this new scenario. We propose Continual-MAML, an online extension of the popular MAML algorithm as a strong baseline for this scenario.
arXiv Detail & Related papers (2020-03-12T15:47:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.