paper-with-me

Papers

Liquid Ensemble Selection for Continual Learning

2024-05-12 · Carter Blair, Ben Armstrong, Kate Larson

Continual learning aims to enable machine learning models to continually learn from a shifting data distribution without forgetting what has already been learned. Such shifting distributions can be broken into disjoint subsets of related examples; by training each member of an ensemble on a different subset it is possible for the ensemble as a whole to achieve much higher accuracy with less forgetting than a naive model. We address the problem of selecting which models within an ensemble should learn on any given data, and which should predict. By drawing on work from delegative voting we develop an algorithm for using delegation to dynamically select which models in an ensemble are active. We explore a variety of delegation methods and performance metrics, ultimately finding that delegation is able to provide a significant performance boost over naive learning in the face of distribution shifts.

📄 PDF Abstract BibTeX arXiv:2405.07327

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Liquid Democracy for Low-Cost Ensemble Pruning

2024-01-30 · Ben Armstrong, Kate Larson

We argue that there is a strong connection between ensemble learning and a delegative voting paradigm -- liquid democracy -- that can be leveraged to reduce ensemble training costs. We present an incremental training pro…

Ensemble LearningEnsemble Pruning

Ensembles and Encoders for Task-Free Continual Learning

2021-09-29 · Murray Shanahan, Christos Kaplanis, Jovana Mitrović

We present an architecture that is effective for continual learning in an especially demanding setting, where task boundaries do not exist or are unknown, and where classes have to be learned online (with each presented …

Continual LearningSelf-Supervised Learning

Encoders and Ensembles for Task-Free Continual Learning

2021-05-27 · Murray Shanahan, Christos Kaplanis, Jovana Mitrović

We present an architecture that is effective for continual learning in an especially demanding setting, where task boundaries do not exist or are unknown, and where classes have to be learned online (with each example pr…

Continual LearningImage ClassificationSelf-Supervised Learning

Continual Learning Beyond a Single Model

2022-02-20 · Thang Doan, Seyed Iman Mirzadeh, Mehrdad Farajtabar

A growing body of research in continual learning focuses on the catastrophic forgetting problem. While many attempts have been made to alleviate this problem, the majority of the methods assume a single model in the cont…

Continual Learningmodel

Adaptive Model Ensemble for Continual Learning

2025-09-24 · Yuchuan Mao, Zhi Gao, Xiaomeng Fan, Yuwei Wu 외 arxiv

Model ensemble is an effective strategy in continual learning, which alleviates catastrophic forgetting by interpolating model parameters, achieving knowledge fusion learned from different tasks. However, existing model …

Continual Learning