arXiv 2305.155912023-05-24cs.LG

面向共享知识终身学习的轻量级学习器

Lightweight Learner for Shared Knowledge Lifelong Learning

University of Southern California（南加州大学）；Intel Labs（英特尔实验室）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）

Yunhao Ge, Yuecheng Li, Di Wu, Ao Xu, Adam M. Jones, Amanda Sofie Rios, Iordanis Fostiropoulos, Shixian Wen, Po-Hsuan Huang, Zachary William Murdock, Gozde Sahi… 展开作者

Yunhao Ge, Yuecheng Li, Di Wu, Ao Xu, Adam M. Jones, Amanda Sofie Rios, Iordanis Fostiropoulos, Shixian Wen, Po-Hsuan Huang, Zachary William Murdock, Gozde Sahin, Shuo Ni, Kiran Lekkala, Sumedh Anand Sontakke, Laurent Itti

备注：: Transactions on Machine Learning Research (TMLR) paper

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出共享知识终身学习（SKILL）挑战，通过去中心化多智能体并行学习并共享轻量级任务模块与任务锚点，在SKILL-102数据集上以近乎完美并行化取得SOTA准确率。

摘要：

在终身学习（LL）中，智能体在遇到新条件和新任务时持续学习。当前大多数终身学习仅限于单个智能体按顺序学习任务，随后部署专门的终身学习机制，以在学习新任务时缓解对旧任务的遗忘。这种方式本质上速度缓慢。我们提出了一项新的共享知识终身学习（SKILL）挑战，该挑战部署了一个去中心化的终身学习智能体群体，每个智能体按顺序学习不同的任务，所有智能体独立并行运行。在学习完各自的任务后，智能体通过去中心化通信网络共享并整合知识，最终使所有智能体都能掌握所有任务。我们提出了SKILL的一种解决方案，该方案使用轻量级终身学习（LLL）智能体，其目标是通过最小化智能体中针对任何给定任务专门化的部分比例来促进高效共享。因此，每个LLL智能体由一个与任务无关的公共不可变部分组成（其中包含大部分参数），以及针对每个任务适配的、参数更少的个体任务特定模块。智能体共享其任务特定模块，以及表示其任务在所有智能体共有的任务无关潜在空间中的摘要信息（“任务锚点”）。接收智能体使用相应的锚点注册每个接收到的任务特定模块。这样，每当收到新的任务特定模块和锚点时，每个智能体解决新任务的能力都会得到提升。在一个全新的、极具挑战性的SKILL-102数据集上（包含102个图像分类任务，共5,033个类别，2,041,225张训练图像，243,464张验证图像和243,464张测试图像），我们取得了远高于8个终身学习基线的准确率（并达到SOTA水平），同时实现了近乎完美的并行化。代码和数据可在 https://github.com/gyhandy/Shared-Knowledge-Lifelong-Learning 获取。

英文摘要：

In Lifelong Learning (LL), agents continually learn as they encounter new conditions and tasks. Most current LL is limited to a single agent that learns tasks sequentially. Dedicated LL machinery is then deployed to mitigate the forgetting of old tasks as new tasks are learned. This is inherently slow. We propose a new Shared Knowledge Lifelong Learning (SKILL) challenge, which deploys a decentralized population of LL agents that each sequentially learn different tasks, with all agents operating independently and in parallel. After learning their respective tasks, agents share and consolidate their knowledge over a decentralized communication network, so that, in the end, all agents can master all tasks. We present one solution to SKILL which uses Lightweight Lifelong Learning (LLL) agents, where the goal is to facilitate efficient sharing by minimizing the fraction of the agent that is specialized for any given task. Each LLL agent thus consists of a common task-agnostic immutable part, where most parameters are, and individual task-specific modules that contain fewer parameters but are adapted to each task. Agents share their task-specific modules, plus summary information ("task anchors") representing their tasks in the common task-agnostic latent space of all agents. Receiving agents register each received task-specific module using the corresponding anchor. Thus, every agent improves its ability to solve new tasks each time new task-specific modules and anchors are received. On a new, very challenging SKILL-102 dataset with 102 image classification tasks (5,033 classes in total, 2,041,225 training, 243,464 validation, and 243,464 test images), we achieve much higher (and SOTA) accuracy over 8 LL baselines, while also achieving near perfect parallelization. Code and data can be found at https://github.com/gyhandy/Shared-Knowledge-Lifelong-Learning

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。