Hierarchically Structured Meta-learning

2019-05-13 · Huaxiu Yao, Ying WEI, Junzhou Huang, Zhenhui Li

In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handled via globally sharing knowledge among tasks. In this paper, based on gradient-based meta-learning, we propose a hierarchically structured meta-learning (HSML) algorithm that explicitly tailors the transferable knowledge to different clusters of tasks. Inspired by the way human beings organize knowledge, we resort to a hierarchical task clustering structure to cluster tasks. As a result, the proposed approach not only addresses the challenge via the knowledge customization to different clusters of tasks, but also preserves knowledge generalization among a cluster of similar tasks. To tackle the changing of task relationship, in addition, we extend the hierarchical structure to a continual learning environment. The experimental results show that our approach can achieve state-of-the-art performance in both toy-regression and few-shot image classification problems.

📄 PDF Abstract BibTeX arXiv:1905.05301

Code (1)

huaxiuyao/HSML 공식 구현 tf

Tasks

ClusteringContinual Learning Few-Shot Image Classification image-classification Image Classification Meta-Learning

Metagross: Meta Gated Recursive Controller Units for Sequence Modeling

2020-01-01 · ICLR 2020 1 · Yi Tay, Yikang Shen, Alvin Chan, Yew Soon Ong

This paper proposes Metagross (Meta Gated Recursive Controller), a new neural sequence modeling unit. Our proposed unit is characterized by recursive parameterization of its gating functions, i.e., gating mechanisms of M…

Code Generation Inductive Bias Machine Translation Music Modeling+2

Microstructure quality control of steels using deep learning

2023-06-01 · Ali Riza Durmaz, Sai Teja Potu, Daniel Romich, Johannes Möller 외

In quality control, microstructures are investigated rigorously to ensure structural integrity, exclude the presence of critical volume defects, and validate the formation of the target microstructure. For quenched, hier…

Decision Making Deep Learning image-classification Image Classification

ELAN as a search engine for hierarchically structured, tagged corpora

2019-01-01 · WS 2019 1 · Joshua Wilbur

Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation

2018-05-21 · Qiuyuan Huang, Zhe Gan, Asli Celikyilmaz, Dapeng Wu 외

We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task. Within our framework, the task…

Decoder Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+4

Meta Learning Shared Hierarchies

2017-10-26 · ICLR 2018 1 · Kevin Frans, Jonathan Ho, Xi Chen, Pieter Abbeel 외

We develop a metalearning approach for learning hierarchically structured policies, improving sample efficiency on unseen tasks through the use of shared primitives---policies that are executed for large numbers of times…

Meta-Learning Reinforcement Learning