U-TELL: Unsupervised Task Expert Lifelong Learning

2024-05-23 · Indu Solomon, Aye Phyu Phyu Aung, Uttam Kumar, Senthilnath Jayavelu

Continual learning (CL) models are designed to learn new tasks arriving sequentially without re-training the network. However, real-world ML applications have very limited label information and these models suffer from catastrophic forgetting. To address these issues, we propose an unsupervised CL model with task experts called Unsupervised Task Expert Lifelong Learning (U-TELL) to continually learn the data arriving in a sequence addressing catastrophic forgetting. During training of U-TELL, we introduce a new expert on arrival of a new task. Our proposed architecture has task experts, a structured data generator and a task assigner. Each task expert is composed of 3 blocks; i) a variational autoencoder to capture the task distribution and perform data abstraction, ii) a k-means clustering module, and iii) a structure extractor to preserve latent task data signature. During testing, task assigner selects a suitable expert to perform clustering. U-TELL does not store or replay task samples, instead, we use generated structured samples to train the task assigner. We compared U-TELL with five SOTA unsupervised CL methods. U-TELL outperformed all baselines on seven benchmarks and one industry dataset for various CL scenarios with a training time over 6 times faster than the best performing baseline.

📄 PDF Abstract BibTeX arXiv:2405.14623

Code (1)

indusolo/unsup_ll 공식 구현 pytorch

Tasks

ClusteringContinual LearningLifelong learning

Methods 이 논문이 사용한 방법론

k-Means Clustering k-Means Clustering is a clustering algorithm that divides a training set into $k$ different clusters of examples that are near each other. It works by initializing $k$…

Evaluation of Lifelong Learning Systems

2020-05-01 · LREC 2020 5 · Yevhenii Prokopalo, Sylvain Meignier, Olivier Galibert, Loic Barrault 외

Current intelligent systems need the expensive support of machine learning experts to sustain their performance level when used on a daily basis. To reduce this cost, i.e. remaining free from any machine learning expert,…

BIG-bench Machine Learning Lifelong learning

LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective

2026-06-24 · Zhihao Gu, Lin Wang arxiv

Building a generalist robot that can leverage prior knowledge for continuous task adaptation remains a significant challenge. Previous works alleviate the catastrophic forgetting problem by parameter-efficient fine-tunin…

parameter-efficient fine-tuning Robot Manipulation

Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts

2024-11-23 · CVPR 2025 1 · Qizhou Chen, Chengyu Wang, Dakan Wang, Taolin Zhang 외

Model editing aims to correct inaccurate knowledge, update outdated information, and incorporate new data into Large Language Models (LLMs) without the need for retraining. This task poses challenges in lifelong scenario…

knowledge editing Mixture-of-Experts Model Editing

Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning

2025-06-06 · YuHeng Lei, Sitong Mao, Shunbo Zhou, Hongyuan Zhang 외

A generalist agent must continuously learn and adapt throughout its lifetime, achieving efficient forward transfer while minimizing catastrophic forgetting. Previous work within the dominant pretrain-then-finetune paradi…

Lifelong learning parameter-efficient fine-tuning

Lifelong Mixture of Variational Autoencoders

2021-07-09 · Fei Ye, Adrian G. Bors

In this paper, we propose an end-to-end lifelong learning mixture of experts. Each expert is implemented by a Variational Autoencoder (VAE). The experts in the mixture system are jointly trained by maximizing a mixture o…

Lifelong learning Mixture-of-Experts