Meta-learning representations with relational structure
B Day - 2023 - repository.cam.ac.uk
Abstract Representation learning has emerged as a versatile tool that is able to take
advantage of the vast datasets acquired using digital technologies. The broad applicability …
advantage of the vast datasets acquired using digital technologies. The broad applicability …
[PDF][PDF] Lecture 8 Meta Representation Learning—Mar. 14, 2024
QL Scribe, M Li - cecilialeiqi.github.io
For average human, it is often easy to use prior knowledge in learning to perform new task,
like we do when distinguishing objects using features extracted from visual information. As …
like we do when distinguishing objects using features extracted from visual information. As …
Conditional meta-learning of linear representations
Standard meta-learning for representation learning aims to find a common representation to
be shared across multiple tasks. The effectiveness of these methods is often limited when …
be shared across multiple tasks. The effectiveness of these methods is often limited when …
[PDF][PDF] Representational issues in meta-learning
A Kalousis, M Hilario - … of the 20th International Conference on …, 2003 - cdn.aaai.org
To address the problem of algorithm selection for the classification task, we equip a
relational case base with new similarity measures that are able to cope with multirelational …
relational case base with new similarity measures that are able to cope with multirelational …
Function contrastive learning of transferable meta-representations
Meta-learning algorithms adapt quickly to new tasks that are drawn from the same task
distribution as the training tasks. The mechanism leading to fast adaptation is the …
distribution as the training tasks. The mechanism leading to fast adaptation is the …
Optimal support features for meta-learning
Meta-learning has many aspects, but its final goal is to discover in an automatic way many
interesting models for a given data. Our early attempts in this area involved heterogeneous …
interesting models for a given data. Our early attempts in this area involved heterogeneous …
Contextualizing meta-learning via learning to decompose
Meta-learning has emerged as an efficient approach for constructing target models based
on support sets. For example, the meta-learned embeddings enable the construction of …
on support sets. For example, the meta-learned embeddings enable the construction of …
Deep representation learning: Fundamentals, perspectives, applications, and open challenges
KT Baghaei, A Payandeh, P Fayyazsanavi… - arXiv preprint arXiv …, 2022 - arxiv.org
Machine Learning algorithms have had a profound impact on the field of computer science
over the past few decades. These algorithms performance is greatly influenced by the …
over the past few decades. These algorithms performance is greatly influenced by the …
Deep representation learning: Fundamentals, technologies, applications, and open challenges
KT Baghaei, A Payandeh, P Fayyazsanavi… - IEEE …, 2023 - ieeexplore.ieee.org
Machine learning algorithms have had a profound impact on the field of computer science
over the past few decades. The performance of these algorithms heavily depends on the …
over the past few decades. The performance of these algorithms heavily depends on the …
[PDF][PDF] Knowledge Acquisition with Transferable and Robust Representation Learning
M Chen - muhaochen.github.io
My research focuses on promoting the advancement of intelligent computational systems
with better awareness of commonsense and expert knowledge, which leads to more efficient …
with better awareness of commonsense and expert knowledge, which leads to more efficient …