paper-with-me

Papers

Modular meta-learning

2018-06-26 · Ferran Alet, Tomás Lozano-Pérez, Leslie P. Kaelbling

Many prediction problems, such as those that arise in the context of robotics, have a simplifying underlying structure that, if known, could accelerate learning. In this paper, we present a strategy for learning a set of neural network modules that can be combined in different ways. We train different modular structures on a set of related tasks and generalize to new tasks by composing the learned modules in new ways. By reusing modules to generalize we achieve combinatorial generalization, akin to the "infinite use of finite means" displayed in language. Finally, we show this improves performance in two robotics-related problems.

📄 PDF Abstract BibTeX arXiv:1806.10166

Code (1)

FerranAlet/modular-metalearning 공식 구현 pytorch

Tasks

Meta-Learning

Similar Papers 제목 키워드 기반

A Parameterized Family of Meta-Submodular Functions

2020-06-23 · Mehrdad Ghadiri, Richard Santiago, Bruce Shepherd

Submodular function maximization has found a wealth of new applications in machine learning models during the past years. The related supermodular maximization models (submodular minimization) also offer an abundance of …

Diversity

A Modular Ontology for MODS -- Metadata Object Description Schema

2023-07-31 · Rushrukh Rayan, Cogan Shimizu, Heidi Sieverding, Pascal Hitzler

The Metadata Object Description Schema (MODS) was developed to describe bibliographic concepts and metadata and is maintained by the Library of Congress. Its authoritative version is given as an XML schema based on an XM…

Knowledge GraphsObject

Modular meta-learning in abstract graph networks for combinatorial generalization

2018-12-19 · Ferran Alet, Maria Bauza, Alberto Rodriguez, Tomas Lozano-Perez 외

Modular meta-learning is a new framework that generalizes to unseen datasets by combining a small set of neural modules in different ways. In this work we propose abstract graph networks: using graphs as abstractions of …

Meta-Learning

A Unified Approach to Submodular Maximization Under Noise

2025-10-24 · Kshipra Bhawalkar, Yang Cai, Zhe Feng, Christopher Liaw 외 arxiv

We consider the problem of maximizing a submodular function with access to a noisy value oracle for the function instead of an exact value oracle. Similar to prior work, we assume that the noisy oracle is persistent in t…

Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks

2021-08-04 · Ivana Nikoloska, Osvaldo Simeone

In this paper, we consider the problem of power control for a wireless network with an arbitrarily time-varying topology, including the possible addition or removal of nodes. A data-driven design methodology that leverag…

Meta-Learning