paper-with-me

Papers

Homomorphisms Between Transfer, Multi-Task, and Meta-Learning Systems

2022-08-04 · Tyler Cody

Transfer learning, multi-task learning, and meta-learning are well-studied topics concerned with the generalization of knowledge across learning tasks and are closely related to general intelligence. But, the formal, general systems differences between them are underexplored in the literature. This lack of systems-level formalism leads to difficulties in coordinating related, inter-disciplinary engineering efforts. This manuscript formalizes transfer learning, multi-task learning, and meta-learning as abstract learning systems, consistent with the formal-minimalist abstract systems theory of Mesarovic and Takahara. Moreover, it uses the presented formalism to relate the three concepts of learning in terms of composition, hierarchy, and structural homomorphism. Findings are readily depicted in terms of input-output systems, highlighting the ease of delineating formal, general systems differences between transfer, multi-task, and meta-learning.

📄 PDF Abstract BibTeX arXiv:2208.03316

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-LearningMulti-Task LearningTransfer Learning

Similar Papers 제목 키워드 기반

Online Abstraction with MDP Homomorphisms for Deep Learning

2018-11-30 · Ondrej Biza, Robert Platt

Abstraction of Markov Decision Processes is a useful tool for solving complex problems, as it can ignore unimportant aspects of an environment, simplifying the process of learning an optimal policy. In this paper, we pro…

Deep Learning

Neural ring homomorphisms and maps between neural codes

2019-02-13

Neural codes are binary codes that are used for information processing and representation in the brain. In previous work, we have shown how an algebraic structure, called the {\it neural ring}, can be used to efficiently…

Bounding Performance Loss in Approximate MDP Homomorphisms

2008-12-01 · NeurIPS 2008 12 · Jonathan Taylor, Doina Precup, Prakash Panagaden

We define a metric for measuring behavior similarity between states in a Markov decision process (MDP), in which action similarity is taken into account. We show that the kernel of our metric corresponds exactly to the c…

Structural Preservation and the Logical Expressiveness of Graph Neural Networks

2026-06-16 · Przemysław Andrzej Wałęga, Bernardo Cuenca Grau arxiv

Bridges between graph neural networks (GNNs) and logical formalisms have been established by fixing architectural choices, such as the types of aggregation, combination, and activation functions. These choices define res…

Continuous MDP Homomorphisms and Homomorphic Policy Gradient

2022-09-15 · Sahand Rezaei-Shoshtari, Rosie Zhao, Prakash Panangaden, David Meger 외

Abstraction has been widely studied as a way to improve the efficiency and generalization of reinforcement learning algorithms. In this paper, we study abstraction in the continuous-control setting. We extend the definit…

continuous-controlContinuous ControlPolicy Gradient MethodsReinforcement Learning (RL)+1